注意
点击 这里 下载完整的示例代码
摆锤：使用 TorchRL 编写环境和变换¶
作者: Vincent Moens
创建环境（模拟器或物理控制系统的接口）是强化学习和控制工程中不可或缺的一部分。
TorchRL 提供了一组工具，可以在多种情况下做到这一点。本教程演示了如何使用 PyTorch 和 TorchRL 从头开始编写摆锤模拟器代码。它从 OpenAI-Gym/Farama-Gymnasium 控制库 的 Pendulum-v1 实现中汲取了灵感。
简单的摆锤¶
关键学习内容
如何在 TorchRL 中设计环境：- 编写规范（输入、观察和奖励）；- 实现行为：播种、重置和步骤。
转换您的环境输入和输出，并编写您自己的转换；
如何使用
TensorDict通过codebase传递任意数据结构。在这个过程中，我们将触及 TorchRL 的三个关键组成部分
为了让您了解使用 TorchRL 环境可以实现什么，我们将设计一个无状态环境。虽然有状态的环境会跟踪遇到的最新物理状态，并依赖于此来模拟状态到状态的转换，但无状态的环境期望在每一步都提供当前状态，以及所采取的行动。TorchRL 支持这两种类型的环境，但无状态环境更通用，因此涵盖了 TorchRL 中环境 API 的更广泛的功能。
对无状态环境进行建模可以让用户完全控制模拟器的输入和输出：用户可以在任何阶段重置实验，或者从外部主动修改动态。然而，这假设我们对任务有一定的控制权，而这可能并非总是如此：解决一个我们无法控制当前状态的问题更具挑战性，但其应用范围更广。
无状态环境的另一个优势是它们可以启用对转换模拟的批量执行。如果后端和实现允许，代数运算可以在标量、向量或张量上无缝执行。本教程提供了此类示例。
本教程将按照以下结构进行。
我们将首先熟悉环境属性：其形状（
batch_size），其方法（主要是step()，reset()和set_seed()）以及最后是其规范。在编写完模拟器后，我们将演示如何在训练过程中使用变换来使用它。
我们将探索 TorchRL API 带来的新途径，包括：转换输入的可能性、模拟的向量化执行以及通过模拟图进行反向传播的可能性。
最后，我们将训练一个简单的策略来解决我们实现的系统。
from collections import defaultdict
from typing import Optional
import numpy as np
import torch
import tqdm
from tensordict import TensorDict, TensorDictBase
from tensordict.nn import TensorDictModule
from torch import nn
from torchrl.data import BoundedTensorSpec, CompositeSpec, UnboundedContinuousTensorSpec
from torchrl.envs import (
CatTensors,
EnvBase,
Transform,
TransformedEnv,
UnsqueezeTransform,
)
from torchrl.envs.transforms.transforms import _apply_to_composite
from torchrl.envs.utils import check_env_specs, step_mdp
DEFAULT_X = np.pi
DEFAULT_Y = 1.0
在设计新的环境类时，您必须注意以下四件事。
EnvBase._reset()，它为在（可能随机的）初始状态下重置模拟器编写代码；EnvBase._step()它为状态转换动态编写代码；EnvBase._set_seed`()它实现种子机制；环境规范。
让我们首先描述手头的问题：我们希望对一个简单的摆进行建模，我们可以在其固定点上控制施加的扭矩。我们的目标是将摆放置在向上位置（根据惯例，角度位置为 0），并使其在该位置静止。为了设计我们的动力系统，我们需要定义两个方程：动作（施加的扭矩）后的运动方程和构成我们目标函数的奖励方程。
对于运动方程，我们将根据以下公式更新角速度
\[\dot{\theta}_{t+1} = \dot{\theta}_t + (3 * g / (2 * L) * \sin(\theta_t) + 3 / (m * L^2) * u) * dt\]
其中 \(\dot{\theta}\) 是以 rad/sec 为单位的角速度，\(g\) 是重力，\(L\) 是摆的长度，\(m\) 是其质量，\(\theta\) 是其角位置，\(u\) 是扭矩。然后根据以下公式更新角度位置
\[\theta_{t+1} = \theta_{t} + \dot{\theta}_{t+1} dt\]
我们将奖励定义为
\[r = -(\theta^2 + 0.1 * \dot{\theta}^2 + 0.001 * u^2)\]
当角度接近 0（摆处于向上位置）、角速度接近 0（没有运动）并且扭矩也为 0 时，该奖励将被最大化。
编码动作的效果：_step()¶
步骤方法是首先要考虑的事情，因为它将编码对我们感兴趣的模拟。在 TorchRL 中，EnvBase 类有一个 EnvBase.step() 方法，该方法接收一个 tensordict.TensorDict 实例，其中包含一个 "action" 条目，指示要采取的操作。
为了便于从该 tensordict 中读取和写入，并确保键与库期望的一致，模拟部分已委托给一个私有的抽象方法 _step()，该方法从 tensordict 中读取输入数据，并使用输出数据写入一个新的 tensordict。
该 _step() 方法应执行以下操作。
读取输入键（例如
"action"）并根据这些键执行模拟；检索观察结果、完成状态和奖励；
将观察值集以及奖励和完成状态写入一个新的
TensorDict中的对应条目。
接下来，step() 方法将 step() 的输出合并到输入 tensordict 中，以强制执行输入/输出一致性。
通常，对于有状态的环境，这将类似于以下内容。
>>> policy(env.reset())
>>> print(tensordict)
TensorDict(
fields={
action: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
observation: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=cpu,
is_shared=False)
>>> env.step(tensordict)
>>> print(tensordict)
TensorDict(
fields={
action: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
next: TensorDict(
fields={
done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
observation: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
reward: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=cpu,
is_shared=False),
observation: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=cpu,
is_shared=False)
请注意，根 tensordict 没有改变，唯一的修改是出现了一个新的 "next" 条目，其中包含新信息。
在摆示例中，我们的 _step() 方法将从输入 tensordict 中读取相关条目，并在 "action" 键编码的力作用于摆后计算摆的位置和速度。我们计算摆的新角位置 "new_th"，它是先前位置 "th" 与新的速度 "new_thdot" 在时间间隔 dt 内的结果。
由于我们的目标是将摆向上翻转并使其在该位置静止，因此我们的 cost（负奖励）函数对于接近目标位置和低速度的位置更低。实际上，我们希望阻止远离“向上”的位置和/或远离 0 的速度。
在我们的示例中，EnvBase._step() 被编码为静态方法，因为我们的环境是无状态的。在有状态的设置中，需要 self 参数，因为需要从环境中读取状态。
def _step(tensordict):
th, thdot = tensordict["th"], tensordict["thdot"] # th := theta
g_force = tensordict["params", "g"]
mass = tensordict["params", "m"]
length = tensordict["params", "l"]
dt = tensordict["params", "dt"]
u = tensordict["action"].squeeze(-1)
u = u.clamp(-tensordict["params", "max_torque"], tensordict["params", "max_torque"])
costs = angle_normalize(th) ** 2 + 0.1 * thdot**2 + 0.001 * (u**2)
new_thdot = (
thdot
+ (3 * g_force / (2 * length) * th.sin() + 3.0 / (mass * length**2) * u) * dt
)
new_thdot = new_thdot.clamp(
-tensordict["params", "max_speed"], tensordict["params", "max_speed"]
)
new_th = th + new_thdot * dt
reward = -costs.view(*tensordict.shape, 1)
done = torch.zeros_like(reward, dtype=torch.bool)
out = TensorDict(
{
"th": new_th,
"thdot": new_thdot,
"params": tensordict["params"],
"reward": reward,
"done": done,
},
tensordict.shape,
)
return out
def angle_normalize(x):
return ((x + torch.pi) % (2 * torch.pi)) - torch.pi
重置模拟器：_reset()¶
我们需要关注的第二个方法是 _reset() 方法。与 _step() 一样，它应将观察条目以及可能完成的状态写入它输出的 tensordict 中（如果省略完成状态，它将由父方法 reset() 填充为 False）。在某些情况下，要求 _reset 方法从调用它的函数中接收命令（例如，在多智能体设置中，我们可能希望指示哪些智能体需要重置）。这就是为什么 _reset() 方法也期望一个 tensordict 作为输入，尽管它可能是空的或 None。
父 EnvBase.reset() 会执行一些简单的检查，例如 EnvBase.step() 会执行的操作，例如确保在输出 tensordict 中返回一个 "done" 状态，并且形状与规范期望的一致。
对我们来说，唯一需要考虑的重要因素是 EnvBase._reset() 是否包含所有预期的观察结果。再次，由于我们使用的是无状态环境，因此我们将在名为 "params" 的嵌套 tensordict 中传递摆的配置。
在此示例中，我们不传递完成状态，因为这不是 _reset() 的强制要求，并且我们的环境是非终止的，因此我们始终期望它为 False。
def _reset(self, tensordict):
if tensordict is None or tensordict.is_empty():
# if no ``tensordict`` is passed, we generate a single set of hyperparameters
# Otherwise, we assume that the input ``tensordict`` contains all the relevant
# parameters to get started.
tensordict = self.gen_params(batch_size=self.batch_size)
high_th = torch.tensor(DEFAULT_X, device=self.device)
high_thdot = torch.tensor(DEFAULT_Y, device=self.device)
low_th = -high_th
low_thdot = -high_thdot
# for non batch-locked environments, the input ``tensordict`` shape dictates the number
# of simulators run simultaneously. In other contexts, the initial
# random state's shape will depend upon the environment batch-size instead.
th = (
torch.rand(tensordict.shape, generator=self.rng, device=self.device)
* (high_th - low_th)
+ low_th
)
thdot = (
torch.rand(tensordict.shape, generator=self.rng, device=self.device)
* (high_thdot - low_thdot)
+ low_thdot
)
out = TensorDict(
{
"th": th,
"thdot": thdot,
"params": tensordict["params"],
},
batch_size=tensordict.shape,
)
return out
环境元数据：env.*_spec¶
规范定义了环境的输入和输出域。规范准确地定义将在运行时接收的张量非常重要，因为它们通常用于在多处理和分布式设置中携带有关环境的信息。它们还可以用于实例化惰性定义的神经网络和测试脚本，而无需实际查询环境（例如，对于现实世界的物理系统来说，这可能很昂贵）。
我们必须在环境中编写四个规范。
EnvBase.observation_spec：这将是一个CompositeSpec实例，其中每个键都是一个观察结果（CompositeSpec可以被视为规范字典）。EnvBase.action_spec：它可以是任何类型的规范，但要求它与输入tensordict中的"action"条目相对应；EnvBase.reward_spec：提供有关奖励空间的信息；EnvBase.done_spec：提供有关完成标志空间的信息。
TorchRL 规范被组织成两个主要容器：input_spec 包含 step 函数读取的信息规范（分为包含动作的 action_spec 和包含所有其他信息的 state_spec），以及 output_spec，它编码 step 输出的规范（observation_spec、reward_spec 和 done_spec）。一般来说，您不应该直接与 output_spec 和 input_spec 交互，而应该只与其内容交互：observation_spec、reward_spec、done_spec、action_spec 和 state_spec。原因是这些规范在 output_spec 和 input_spec 中以非平凡的方式组织，并且不应该直接修改其中任何一个。
换句话说，observation_spec 和相关属性是输出和输入规范容器内容的便捷快捷方式。
TorchRL 提供了多个 TensorSpec 子类 来编码环境的输入和输出特征。
规范形状¶
环境规范的前导维度必须与环境批次大小匹配。这样做是为了强制执行环境的每个组件（包括其转换）都具有对预期输入和输出形状的准确表示。这在有状态设置中应该被准确地编码。
对于非批次锁定环境，例如我们示例中的环境（见下文），这无关紧要，因为环境批次大小很可能为空。
def _make_spec(self, td_params):
# Under the hood, this will populate self.output_spec["observation"]
self.observation_spec = CompositeSpec(
th=BoundedTensorSpec(
low=-torch.pi,
high=torch.pi,
shape=(),
dtype=torch.float32,
),
thdot=BoundedTensorSpec(
low=-td_params["params", "max_speed"],
high=td_params["params", "max_speed"],
shape=(),
dtype=torch.float32,
),
# we need to add the ``params`` to the observation specs, as we want
# to pass it at each step during a rollout
params=make_composite_from_td(td_params["params"]),
shape=(),
)
# since the environment is stateless, we expect the previous output as input.
# For this, ``EnvBase`` expects some state_spec to be available
self.state_spec = self.observation_spec.clone()
# action-spec will be automatically wrapped in input_spec when
# `self.action_spec = spec` will be called supported
self.action_spec = BoundedTensorSpec(
low=-td_params["params", "max_torque"],
high=td_params["params", "max_torque"],
shape=(1,),
dtype=torch.float32,
)
self.reward_spec = UnboundedContinuousTensorSpec(shape=(*td_params.shape, 1))
def make_composite_from_td(td):
# custom function to convert a ``tensordict`` in a similar spec structure
# of unbounded values.
composite = CompositeSpec(
{
key: make_composite_from_td(tensor)
if isinstance(tensor, TensorDictBase)
else UnboundedContinuousTensorSpec(
dtype=tensor.dtype, device=tensor.device, shape=tensor.shape
)
for key, tensor in td.items()
},
shape=td.shape,
)
return composite
可重复的实验：播种¶
在初始化实验时，播种环境是一种常见的操作。EnvBase._set_seed() 的唯一目标是设置所包含模拟器的种子。如果可能，此操作不应调用 reset() 或与环境执行交互。父级 EnvBase.set_seed() 方法包含一种机制，允许使用不同的伪随机且可重复的种子播种多个环境。
def _set_seed(self, seed: Optional[int]):
rng = torch.manual_seed(seed)
self.rng = rng
将所有东西整合在一起：EnvBase 类¶
我们终于可以将这些部分拼凑起来，设计我们的环境类。规范初始化需要在环境构建期间执行，因此我们必须注意在 PendulumEnv.__init__() 中调用 _make_spec() 方法。
我们添加了一个静态方法 PendulumEnv.gen_params()，它确定性地生成一组在执行期间使用的超参数
def gen_params(g=10.0, batch_size=None) -> TensorDictBase:
"""Returns a ``tensordict`` containing the physical parameters such as gravitational force and torque or speed limits."""
if batch_size is None:
batch_size = []
td = TensorDict(
{
"params": TensorDict(
{
"max_speed": 8,
"max_torque": 2.0,
"dt": 0.05,
"g": g,
"m": 1.0,
"l": 1.0,
},
[],
)
},
[],
)
if batch_size:
td = td.expand(batch_size).contiguous()
return td
我们将环境定义为非 batch_locked，方法是将 homonymous 属性设置为 False。这意味着我们**不会**强制执行输入 tensordict 具有与环境匹配的 batch-size。
以下代码将把我们上面编码的部分拼凑起来。
class PendulumEnv(EnvBase):
metadata = {
"render_modes": ["human", "rgb_array"],
"render_fps": 30,
}
batch_locked = False
def __init__(self, td_params=None, seed=None, device="cpu"):
if td_params is None:
td_params = self.gen_params()
super().__init__(device=device, batch_size=[])
self._make_spec(td_params)
if seed is None:
seed = torch.empty((), dtype=torch.int64).random_().item()
self.set_seed(seed)
# Helpers: _make_step and gen_params
gen_params = staticmethod(gen_params)
_make_spec = _make_spec
# Mandatory methods: _step, _reset and _set_seed
_reset = _reset
_step = staticmethod(_step)
_set_seed = _set_seed
测试我们的环境¶
TorchRL 提供了一个简单的函数 check_env_specs() 来检查（转换后的）环境是否具有与其规范规定的输入/输出结构匹配的结构。让我们试一试
env = PendulumEnv()
check_env_specs(env)
我们可以查看我们的规范，以便对环境签名有一个直观的表示
print("observation_spec:", env.observation_spec)
print("state_spec:", env.state_spec)
print("reward_spec:", env.reward_spec)
observation_spec: CompositeSpec(
th: BoundedTensorSpec(
shape=torch.Size([]),
space=ContinuousBox(
low=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True),
high=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True)),
device=cpu,
dtype=torch.float32,
domain=continuous),
thdot: BoundedTensorSpec(
shape=torch.Size([]),
space=ContinuousBox(
low=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True),
high=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True)),
device=cpu,
dtype=torch.float32,
domain=continuous),
params: CompositeSpec(
max_speed: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.int64,
domain=discrete),
max_torque: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
dt: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
g: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
m: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
l: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
device=cpu,
shape=torch.Size([])),
device=cpu,
shape=torch.Size([]))
state_spec: CompositeSpec(
th: BoundedTensorSpec(
shape=torch.Size([]),
space=ContinuousBox(
low=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True),
high=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True)),
device=cpu,
dtype=torch.float32,
domain=continuous),
thdot: BoundedTensorSpec(
shape=torch.Size([]),
space=ContinuousBox(
low=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True),
high=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True)),
device=cpu,
dtype=torch.float32,
domain=continuous),
params: CompositeSpec(
max_speed: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.int64,
domain=discrete),
max_torque: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
dt: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
g: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
m: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
l: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
device=cpu,
shape=torch.Size([])),
device=cpu,
shape=torch.Size([]))
reward_spec: UnboundedContinuousTensorSpec(
shape=torch.Size([1]),
space=ContinuousBox(
low=Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float32, contiguous=True),
high=Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float32, contiguous=True)),
device=cpu,
dtype=torch.float32,
domain=continuous)
我们还可以执行一些命令来检查输出结构是否符合预期。
td = env.reset()
print("reset tensordict", td)
reset tensordict TensorDict(
fields={
done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=None,
is_shared=False),
terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=None,
is_shared=False)
我们可以运行 env.rand_step() 来从 action_spec 域中随机生成一个动作。由于我们的环境是无状态的，因此必须传递包含超参数和当前状态的 tensordict。在有状态环境中，env.rand_step() 也能完美地工作。
td = env.rand_step(td)
print("random step tensordict", td)
random step tensordict TensorDict(
fields={
action: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
next: TensorDict(
fields={
done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=None,
is_shared=False),
reward: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=None,
is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=None,
is_shared=False),
terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=None,
is_shared=False)
转换环境¶
为无状态模拟器编写环境转换比为有状态模拟器编写稍微复杂一些：转换需要在下一迭代中读取的输出条目需要在下一步骤调用 meth.step() 之前应用逆转换。这是一个展示 TorchRL 转换所有功能的理想场景！
例如，在以下转换后的环境中，我们 unsqueeze 了条目 ["th", "thdot"]，以便能够将它们沿着最后一个维度堆叠起来。我们还将它们作为 in_keys_inv 传递，以便在它们在下一迭代中作为输入传递时将它们挤压回原始形状。
env = TransformedEnv(
env,
# ``Unsqueeze`` the observations that we will concatenate
UnsqueezeTransform(
unsqueeze_dim=-1,
in_keys=["th", "thdot"],
in_keys_inv=["th", "thdot"],
),
)
编写自定义转换¶
TorchRL 的转换可能无法涵盖人们希望在执行环境后执行的所有操作。编写转换并不需要太多努力。与环境设计一样，编写转换有两个步骤
使动力学正确（正向和反向）；
调整环境规范。
转换可以在两种情况下使用：它本身可以用作 Module。它也可以用作附加到 TransformedEnv 的项。类的结构允许在不同的上下文中自定义行为。
一个 Transform 的骨架可以概括如下
class Transform(nn.Module):
def forward(self, tensordict):
...
def _apply_transform(self, tensordict):
...
def _step(self, tensordict):
...
def _call(self, tensordict):
...
def inv(self, tensordict):
...
def _inv_apply_transform(self, tensordict):
...
有三个入口点（forward()、_step() 和 inv()），它们都接收 tensordict.TensorDict 实例。前两个最终将通过 in_keys 指示的键并调用 _apply_transform() 来对其中的每一个进行操作。结果将被写入由 Transform.out_keys 指示的条目（如果没有提供，则将使用转换后的值更新 in_keys）。如果需要执行逆转换，将执行类似的数据流，但使用 Transform.inv() 和 Transform._inv_apply_transform() 方法以及跨 in_keys_inv 和 out_keys_inv 的键列表执行。下图总结了环境和回放缓冲区中的这种流程。
转换 API
在某些情况下，转换不会以单一的方式对键的子集进行操作，而是对父环境执行某些操作或使用整个输入 tensordict。在这些情况下，应重新编写 _call() 和 forward() 方法，可以跳过 _apply_transform() 方法。
让我们编写新的转换，它将计算位置角的 sine 和 cosine 值，因为这些值对我们学习策略比原始角值更有用
class SinTransform(Transform):
def _apply_transform(self, obs: torch.Tensor) -> None:
return obs.sin()
# The transform must also modify the data at reset time
def _reset(
self, tensordict: TensorDictBase, tensordict_reset: TensorDictBase
) -> TensorDictBase:
return self._call(tensordict_reset)
# _apply_to_composite will execute the observation spec transform across all
# in_keys/out_keys pairs and write the result in the observation_spec which
# is of type ``Composite``
@_apply_to_composite
def transform_observation_spec(self, observation_spec):
return BoundedTensorSpec(
low=-1,
high=1,
shape=observation_spec.shape,
dtype=observation_spec.dtype,
device=observation_spec.device,
)
class CosTransform(Transform):
def _apply_transform(self, obs: torch.Tensor) -> None:
return obs.cos()
# The transform must also modify the data at reset time
def _reset(
self, tensordict: TensorDictBase, tensordict_reset: TensorDictBase
) -> TensorDictBase:
return self._call(tensordict_reset)
# _apply_to_composite will execute the observation spec transform across all
# in_keys/out_keys pairs and write the result in the observation_spec which
# is of type ``Composite``
@_apply_to_composite
def transform_observation_spec(self, observation_spec):
return BoundedTensorSpec(
low=-1,
high=1,
shape=observation_spec.shape,
dtype=observation_spec.dtype,
device=observation_spec.device,
)
t_sin = SinTransform(in_keys=["th"], out_keys=["sin"])
t_cos = CosTransform(in_keys=["th"], out_keys=["cos"])
env.append_transform(t_sin)
env.append_transform(t_cos)
TransformedEnv(
env=PendulumEnv(),
transform=Compose(
UnsqueezeTransform(unsqueeze_dim=-1, in_keys=['th', 'thdot'], out_keys=['th', 'thdot'], in_keys_inv=['th', 'thdot'], out_keys_inv=['th', 'thdot']),
SinTransform(keys=['th']),
CosTransform(keys=['th'])))
将观测值连接到“观测值”条目。 del_keys=False 确保我们为下一迭代保留这些值。
cat_transform = CatTensors(
in_keys=["sin", "cos", "thdot"], dim=-1, out_key="observation", del_keys=False
)
env.append_transform(cat_transform)
TransformedEnv(
env=PendulumEnv(),
transform=Compose(
UnsqueezeTransform(unsqueeze_dim=-1, in_keys=['th', 'thdot'], out_keys=['th', 'thdot'], in_keys_inv=['th', 'thdot'], out_keys_inv=['th', 'thdot']),
SinTransform(keys=['th']),
CosTransform(keys=['th']),
CatTensors(in_keys=['cos', 'sin', 'thdot'], out_key=observation)))
再次，让我们检查我们的环境规范是否与接收到的内容匹配
check_env_specs(env)
执行展开¶
执行展开是一系列简单的步骤
重置环境
当某些条件未满足时
根据策略计算动作
根据该动作执行一步
收集数据
执行一个
MDP步骤
收集数据并返回
这些操作已方便地封装在 rollout() 方法中，我们在这里提供了简化版本。
def simple_rollout(steps=100):
# preallocate:
data = TensorDict({}, [steps])
# reset
_data = env.reset()
for i in range(steps):
_data["action"] = env.action_spec.rand()
_data = env.step(_data)
data[i] = _data
_data = step_mdp(_data, keep_other=True)
return data
print("data from rollout:", simple_rollout(100))
data from rollout: TensorDict(
fields={
action: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
cos: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
next: TensorDict(
fields={
cos: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
observation: Tensor(shape=torch.Size([100, 3]), device=cpu, dtype=torch.float32, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([100]),
device=None,
is_shared=False),
reward: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
sin: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([100]),
device=None,
is_shared=False),
observation: Tensor(shape=torch.Size([100, 3]), device=cpu, dtype=torch.float32, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([100]),
device=None,
is_shared=False),
sin: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([100]),
device=None,
is_shared=False)
批量计算¶
我们教程中最后一个未探索的方面是我们对 TorchRL 中批量计算的能力。因为我们的环境对输入数据形状没有任何假设，所以我们可以无缝地对数据批次进行执行。更棒的是：对于非批次锁定环境（如我们的 Pendulum），我们可以动态地更改批次大小，而无需重新创建环境。为此，我们只需生成具有所需形状的参数。
batch_size = 10 # number of environments to be executed in batch
td = env.reset(env.gen_params(batch_size=[batch_size]))
print("reset (batch size of 10)", td)
td = env.rand_step(td)
print("rand step (batch size of 10)", td)
reset (batch size of 10) TensorDict(
fields={
cos: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.bool, is_shared=False),
observation: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10]),
device=None,
is_shared=False),
sin: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10]),
device=None,
is_shared=False)
rand step (batch size of 10) TensorDict(
fields={
action: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
cos: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.bool, is_shared=False),
next: TensorDict(
fields={
cos: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.bool, is_shared=False),
observation: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10]),
device=None,
is_shared=False),
reward: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
sin: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10]),
device=None,
is_shared=False),
observation: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10]),
device=None,
is_shared=False),
sin: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10]),
device=None,
is_shared=False)
使用一批数据执行展开需要我们在展开函数之外重置环境，因为我们需要动态定义批次大小，而这在 rollout() 中不支持。
rollout = env.rollout(
3,
auto_reset=False, # we're executing the reset out of the ``rollout`` call
tensordict=env.reset(env.gen_params(batch_size=[batch_size])),
)
print("rollout of len 3 (batch size of 10):", rollout)
rollout of len 3 (batch size of 10): TensorDict(
fields={
action: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
cos: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.bool, is_shared=False),
next: TensorDict(
fields={
cos: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.bool, is_shared=False),
observation: Tensor(shape=torch.Size([10, 3, 3]), device=cpu, dtype=torch.float32, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10, 3]),
device=None,
is_shared=False),
reward: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
sin: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10, 3]),
device=None,
is_shared=False),
observation: Tensor(shape=torch.Size([10, 3, 3]), device=cpu, dtype=torch.float32, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10, 3]),
device=None,
is_shared=False),
sin: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10, 3]),
device=None,
is_shared=False)
训练简单的策略¶
在这个示例中，我们将使用奖励作为可微分的目标（例如负损失）来训练一个简单的策略。我们将利用我们的动态系统是完全可微分的这一事实，通过轨迹回报进行反向传播，并直接调整策略的权重以最大化此值。当然，在许多设置中，我们做出的许多假设并不成立，例如可微分的系统和对底层机制的完全访问权限。
当然，这是一个非常简单的例子，展示了如何在 TorchRL 中使用自定义环境编写训练循环。
让我们先编写策略网络
torch.manual_seed(0)
env.set_seed(0)
net = nn.Sequential(
nn.LazyLinear(64),
nn.Tanh(),
nn.LazyLinear(64),
nn.Tanh(),
nn.LazyLinear(64),
nn.Tanh(),
nn.LazyLinear(1),
)
policy = TensorDictModule(
net,
in_keys=["observation"],
out_keys=["action"],
)
以及我们的优化器
optim = torch.optim.Adam(policy.parameters(), lr=2e-3)
训练循环¶
我们将依次
生成轨迹
累加奖励
通过这些操作定义的图进行反向传播
裁剪梯度范数并进行优化步骤
重复
在训练循环结束时，我们应该得到一个接近 0 的最终奖励，这表明摆锤向上并且像预期那样静止。
batch_size = 32
pbar = tqdm.tqdm(range(20_000 // batch_size))
scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optim, 20_000)
logs = defaultdict(list)
for _ in pbar:
init_td = env.reset(env.gen_params(batch_size=[batch_size]))
rollout = env.rollout(100, policy, tensordict=init_td, auto_reset=False)
traj_return = rollout["next", "reward"].mean()
(-traj_return).backward()
gn = torch.nn.utils.clip_grad_norm_(net.parameters(), 1.0)
optim.step()
optim.zero_grad()
pbar.set_description(
f"reward: {traj_return: 4.4f}, "
f"last reward: {rollout[..., -1]['next', 'reward'].mean(): 4.4f}, gradient norm: {gn: 4.4}"
)
logs["return"].append(traj_return.item())
logs["last_reward"].append(rollout[..., -1]["next", "reward"].mean().item())
scheduler.step()
def plot():
import matplotlib
from matplotlib import pyplot as plt
is_ipython = "inline" in matplotlib.get_backend()
if is_ipython:
from IPython import display
with plt.ion():
plt.figure(figsize=(10, 5))
plt.subplot(1, 2, 1)
plt.plot(logs["return"])
plt.title("returns")
plt.xlabel("iteration")
plt.subplot(1, 2, 2)
plt.plot(logs["last_reward"])
plt.title("last reward")
plt.xlabel("iteration")
if is_ipython:
display.display(plt.gcf())
display.clear_output(wait=True)
plt.show()
plot()
0%| | 0/625 [00:00<?, ?it/s]
reward: -6.0488, last reward: -5.0748, gradient norm: 8.519: 0%| | 0/625 [00:00<?, ?it/s]
reward: -6.0488, last reward: -5.0748, gradient norm: 8.519: 0%| | 1/625 [00:00<01:30, 6.92it/s]
reward: -7.0499, last reward: -7.4472, gradient norm: 5.073: 0%| | 1/625 [00:00<01:30, 6.92it/s]
reward: -7.0499, last reward: -7.4472, gradient norm: 5.073: 0%| | 2/625 [00:00<01:30, 6.87it/s]
reward: -7.0685, last reward: -7.0408, gradient norm: 5.552: 0%| | 2/625 [00:00<01:30, 6.87it/s]
reward: -7.0685, last reward: -7.0408, gradient norm: 5.552: 0%| | 3/625 [00:00<01:29, 6.94it/s]
reward: -6.5154, last reward: -5.9086, gradient norm: 2.527: 0%| | 3/625 [00:00<01:29, 6.94it/s]
reward: -6.5154, last reward: -5.9086, gradient norm: 2.527: 1%| | 4/625 [00:00<01:29, 6.96it/s]
reward: -6.2006, last reward: -5.9385, gradient norm: 8.155: 1%| | 4/625 [00:00<01:29, 6.96it/s]
reward: -6.2006, last reward: -5.9385, gradient norm: 8.155: 1%| | 5/625 [00:00<01:28, 6.99it/s]
reward: -6.2568, last reward: -5.4981, gradient norm: 6.223: 1%| | 5/625 [00:00<01:28, 6.99it/s]
reward: -6.2568, last reward: -5.4981, gradient norm: 6.223: 1%| | 6/625 [00:00<01:29, 6.92it/s]
reward: -5.8929, last reward: -8.4491, gradient norm: 4.581: 1%| | 6/625 [00:01<01:29, 6.92it/s]
reward: -5.8929, last reward: -8.4491, gradient norm: 4.581: 1%|1 | 7/625 [00:01<01:29, 6.94it/s]
reward: -6.3233, last reward: -9.0664, gradient norm: 7.596: 1%|1 | 7/625 [00:01<01:29, 6.94it/s]
reward: -6.3233, last reward: -9.0664, gradient norm: 7.596: 1%|1 | 8/625 [00:01<01:28, 6.97it/s]
reward: -6.1021, last reward: -9.5263, gradient norm: 0.9579: 1%|1 | 8/625 [00:01<01:28, 6.97it/s]
reward: -6.1021, last reward: -9.5263, gradient norm: 0.9579: 1%|1 | 9/625 [00:01<01:28, 6.99it/s]
reward: -6.5807, last reward: -8.8075, gradient norm: 3.212: 1%|1 | 9/625 [00:01<01:28, 6.99it/s]
reward: -6.5807, last reward: -8.8075, gradient norm: 3.212: 2%|1 | 10/625 [00:01<01:27, 7.00it/s]
reward: -6.2009, last reward: -8.5525, gradient norm: 2.914: 2%|1 | 10/625 [00:01<01:27, 7.00it/s]
reward: -6.2009, last reward: -8.5525, gradient norm: 2.914: 2%|1 | 11/625 [00:01<01:28, 6.96it/s]
reward: -6.2894, last reward: -8.0115, gradient norm: 52.06: 2%|1 | 11/625 [00:01<01:28, 6.96it/s]
reward: -6.2894, last reward: -8.0115, gradient norm: 52.06: 2%|1 | 12/625 [00:01<01:28, 6.93it/s]
reward: -6.0977, last reward: -6.1845, gradient norm: 18.09: 2%|1 | 12/625 [00:01<01:28, 6.93it/s]
reward: -6.0977, last reward: -6.1845, gradient norm: 18.09: 2%|2 | 13/625 [00:01<01:28, 6.89it/s]
reward: -6.1830, last reward: -7.4858, gradient norm: 5.233: 2%|2 | 13/625 [00:02<01:28, 6.89it/s]
reward: -6.1830, last reward: -7.4858, gradient norm: 5.233: 2%|2 | 14/625 [00:02<01:28, 6.87it/s]
reward: -6.2863, last reward: -5.0297, gradient norm: 1.464: 2%|2 | 14/625 [00:02<01:28, 6.87it/s]
reward: -6.2863, last reward: -5.0297, gradient norm: 1.464: 2%|2 | 15/625 [00:02<01:28, 6.87it/s]
reward: -6.4617, last reward: -5.5997, gradient norm: 2.904: 2%|2 | 15/625 [00:02<01:28, 6.87it/s]
reward: -6.4617, last reward: -5.5997, gradient norm: 2.904: 3%|2 | 16/625 [00:02<01:28, 6.87it/s]
reward: -6.1647, last reward: -6.0777, gradient norm: 4.901: 3%|2 | 16/625 [00:02<01:28, 6.87it/s]
reward: -6.1647, last reward: -6.0777, gradient norm: 4.901: 3%|2 | 17/625 [00:02<01:29, 6.83it/s]
reward: -6.4709, last reward: -6.6813, gradient norm: 0.8317: 3%|2 | 17/625 [00:02<01:29, 6.83it/s]
reward: -6.4709, last reward: -6.6813, gradient norm: 0.8317: 3%|2 | 18/625 [00:02<01:29, 6.81it/s]
reward: -6.3221, last reward: -6.5554, gradient norm: 1.276: 3%|2 | 18/625 [00:02<01:29, 6.81it/s]
reward: -6.3221, last reward: -6.5554, gradient norm: 1.276: 3%|3 | 19/625 [00:02<01:29, 6.79it/s]
reward: -6.3353, last reward: -7.9999, gradient norm: 4.701: 3%|3 | 19/625 [00:02<01:29, 6.79it/s]
reward: -6.3353, last reward: -7.9999, gradient norm: 4.701: 3%|3 | 20/625 [00:02<01:29, 6.78it/s]
reward: -5.8570, last reward: -7.6656, gradient norm: 5.463: 3%|3 | 20/625 [00:03<01:29, 6.78it/s]
reward: -5.8570, last reward: -7.6656, gradient norm: 5.463: 3%|3 | 21/625 [00:03<01:28, 6.79it/s]
reward: -5.7779, last reward: -6.6911, gradient norm: 6.875: 3%|3 | 21/625 [00:03<01:28, 6.79it/s]
reward: -5.7779, last reward: -6.6911, gradient norm: 6.875: 4%|3 | 22/625 [00:03<01:28, 6.82it/s]
reward: -6.0796, last reward: -5.7082, gradient norm: 5.308: 4%|3 | 22/625 [00:03<01:28, 6.82it/s]
reward: -6.0796, last reward: -5.7082, gradient norm: 5.308: 4%|3 | 23/625 [00:03<01:27, 6.85it/s]
reward: -6.0421, last reward: -6.1496, gradient norm: 12.4: 4%|3 | 23/625 [00:03<01:27, 6.85it/s]
reward: -6.0421, last reward: -6.1496, gradient norm: 12.4: 4%|3 | 24/625 [00:03<01:27, 6.87it/s]
reward: -5.5037, last reward: -5.1755, gradient norm: 22.62: 4%|3 | 24/625 [00:03<01:27, 6.87it/s]
reward: -5.5037, last reward: -5.1755, gradient norm: 22.62: 4%|4 | 25/625 [00:03<01:26, 6.92it/s]
reward: -5.5029, last reward: -4.9454, gradient norm: 3.665: 4%|4 | 25/625 [00:03<01:26, 6.92it/s]
reward: -5.5029, last reward: -4.9454, gradient norm: 3.665: 4%|4 | 26/625 [00:03<01:26, 6.94it/s]
reward: -5.9330, last reward: -6.2118, gradient norm: 5.444: 4%|4 | 26/625 [00:03<01:26, 6.94it/s]
reward: -5.9330, last reward: -6.2118, gradient norm: 5.444: 4%|4 | 27/625 [00:03<01:26, 6.92it/s]
reward: -6.0995, last reward: -6.6294, gradient norm: 11.69: 4%|4 | 27/625 [00:04<01:26, 6.92it/s]
reward: -6.0995, last reward: -6.6294, gradient norm: 11.69: 4%|4 | 28/625 [00:04<01:25, 6.95it/s]
reward: -6.3146, last reward: -7.2909, gradient norm: 5.461: 4%|4 | 28/625 [00:04<01:25, 6.95it/s]
reward: -6.3146, last reward: -7.2909, gradient norm: 5.461: 5%|4 | 29/625 [00:04<01:26, 6.92it/s]
reward: -5.9720, last reward: -6.1298, gradient norm: 19.91: 5%|4 | 29/625 [00:04<01:26, 6.92it/s]
reward: -5.9720, last reward: -6.1298, gradient norm: 19.91: 5%|4 | 30/625 [00:04<01:25, 6.92it/s]
reward: -5.9923, last reward: -7.0345, gradient norm: 3.464: 5%|4 | 30/625 [00:04<01:25, 6.92it/s]
reward: -5.9923, last reward: -7.0345, gradient norm: 3.464: 5%|4 | 31/625 [00:04<01:26, 6.90it/s]
reward: -5.3438, last reward: -4.3688, gradient norm: 2.424: 5%|4 | 31/625 [00:04<01:26, 6.90it/s]
reward: -5.3438, last reward: -4.3688, gradient norm: 2.424: 5%|5 | 32/625 [00:04<01:26, 6.86it/s]
reward: -5.6953, last reward: -4.5233, gradient norm: 3.411: 5%|5 | 32/625 [00:04<01:26, 6.86it/s]
reward: -5.6953, last reward: -4.5233, gradient norm: 3.411: 5%|5 | 33/625 [00:04<01:26, 6.85it/s]
reward: -5.4288, last reward: -2.8011, gradient norm: 10.82: 5%|5 | 33/625 [00:04<01:26, 6.85it/s]
reward: -5.4288, last reward: -2.8011, gradient norm: 10.82: 5%|5 | 34/625 [00:04<01:26, 6.86it/s]
reward: -5.5329, last reward: -4.2677, gradient norm: 15.71: 5%|5 | 34/625 [00:05<01:26, 6.86it/s]
reward: -5.5329, last reward: -4.2677, gradient norm: 15.71: 6%|5 | 35/625 [00:05<01:25, 6.91it/s]
reward: -5.6969, last reward: -3.7010, gradient norm: 1.376: 6%|5 | 35/625 [00:05<01:25, 6.91it/s]
reward: -5.6969, last reward: -3.7010, gradient norm: 1.376: 6%|5 | 36/625 [00:05<01:25, 6.90it/s]
reward: -5.9352, last reward: -4.7707, gradient norm: 15.49: 6%|5 | 36/625 [00:05<01:25, 6.90it/s]
reward: -5.9352, last reward: -4.7707, gradient norm: 15.49: 6%|5 | 37/625 [00:05<01:24, 6.93it/s]
reward: -5.6178, last reward: -4.5646, gradient norm: 3.348: 6%|5 | 37/625 [00:05<01:24, 6.93it/s]
reward: -5.6178, last reward: -4.5646, gradient norm: 3.348: 6%|6 | 38/625 [00:05<01:25, 6.89it/s]
reward: -5.7304, last reward: -3.9407, gradient norm: 4.942: 6%|6 | 38/625 [00:05<01:25, 6.89it/s]
reward: -5.7304, last reward: -3.9407, gradient norm: 4.942: 6%|6 | 39/625 [00:05<01:25, 6.89it/s]
reward: -5.3882, last reward: -3.7604, gradient norm: 9.85: 6%|6 | 39/625 [00:05<01:25, 6.89it/s]
reward: -5.3882, last reward: -3.7604, gradient norm: 9.85: 6%|6 | 40/625 [00:05<01:25, 6.88it/s]
reward: -5.3507, last reward: -2.8928, gradient norm: 1.258: 6%|6 | 40/625 [00:05<01:25, 6.88it/s]
reward: -5.3507, last reward: -2.8928, gradient norm: 1.258: 7%|6 | 41/625 [00:05<01:24, 6.88it/s]
reward: -5.6978, last reward: -4.4641, gradient norm: 4.549: 7%|6 | 41/625 [00:06<01:24, 6.88it/s]
reward: -5.6978, last reward: -4.4641, gradient norm: 4.549: 7%|6 | 42/625 [00:06<01:24, 6.92it/s]
reward: -5.5263, last reward: -3.6047, gradient norm: 2.544: 7%|6 | 42/625 [00:06<01:24, 6.92it/s]
reward: -5.5263, last reward: -3.6047, gradient norm: 2.544: 7%|6 | 43/625 [00:06<01:24, 6.90it/s]
reward: -5.5005, last reward: -4.4136, gradient norm: 11.49: 7%|6 | 43/625 [00:06<01:24, 6.90it/s]
reward: -5.5005, last reward: -4.4136, gradient norm: 11.49: 7%|7 | 44/625 [00:06<01:24, 6.87it/s]
reward: -5.2993, last reward: -6.3222, gradient norm: 32.53: 7%|7 | 44/625 [00:06<01:24, 6.87it/s]
reward: -5.2993, last reward: -6.3222, gradient norm: 32.53: 7%|7 | 45/625 [00:06<01:24, 6.88it/s]
reward: -5.4046, last reward: -5.7314, gradient norm: 7.275: 7%|7 | 45/625 [00:06<01:24, 6.88it/s]
reward: -5.4046, last reward: -5.7314, gradient norm: 7.275: 7%|7 | 46/625 [00:06<01:24, 6.87it/s]
reward: -5.6331, last reward: -4.9318, gradient norm: 6.961: 7%|7 | 46/625 [00:06<01:24, 6.87it/s]
reward: -5.6331, last reward: -4.9318, gradient norm: 6.961: 8%|7 | 47/625 [00:06<01:24, 6.87it/s]
reward: -4.8331, last reward: -4.1604, gradient norm: 26.26: 8%|7 | 47/625 [00:06<01:24, 6.87it/s]
reward: -4.8331, last reward: -4.1604, gradient norm: 26.26: 8%|7 | 48/625 [00:06<01:23, 6.91it/s]
reward: -5.4099, last reward: -4.4761, gradient norm: 8.125: 8%|7 | 48/625 [00:07<01:23, 6.91it/s]
reward: -5.4099, last reward: -4.4761, gradient norm: 8.125: 8%|7 | 49/625 [00:07<01:23, 6.92it/s]
reward: -5.4262, last reward: -3.6363, gradient norm: 2.382: 8%|7 | 49/625 [00:07<01:23, 6.92it/s]
reward: -5.4262, last reward: -3.6363, gradient norm: 2.382: 8%|8 | 50/625 [00:07<01:22, 6.96it/s]
reward: -5.3593, last reward: -5.7377, gradient norm: 22.62: 8%|8 | 50/625 [00:07<01:22, 6.96it/s]
reward: -5.3593, last reward: -5.7377, gradient norm: 22.62: 8%|8 | 51/625 [00:07<01:22, 6.97it/s]
reward: -5.2847, last reward: -3.3443, gradient norm: 2.867: 8%|8 | 51/625 [00:07<01:22, 6.97it/s]
reward: -5.2847, last reward: -3.3443, gradient norm: 2.867: 8%|8 | 52/625 [00:07<01:22, 6.92it/s]
reward: -5.3592, last reward: -6.4760, gradient norm: 8.441: 8%|8 | 52/625 [00:07<01:22, 6.92it/s]
reward: -5.3592, last reward: -6.4760, gradient norm: 8.441: 8%|8 | 53/625 [00:07<01:23, 6.87it/s]
reward: -5.9950, last reward: -10.8021, gradient norm: 11.77: 8%|8 | 53/625 [00:07<01:23, 6.87it/s]
reward: -5.9950, last reward: -10.8021, gradient norm: 11.77: 9%|8 | 54/625 [00:07<01:23, 6.83it/s]
reward: -6.3528, last reward: -7.1214, gradient norm: 7.708: 9%|8 | 54/625 [00:07<01:23, 6.83it/s]
reward: -6.3528, last reward: -7.1214, gradient norm: 7.708: 9%|8 | 55/625 [00:07<01:23, 6.81it/s]
reward: -6.4023, last reward: -7.3583, gradient norm: 9.041: 9%|8 | 55/625 [00:08<01:23, 6.81it/s]
reward: -6.4023, last reward: -7.3583, gradient norm: 9.041: 9%|8 | 56/625 [00:08<01:23, 6.79it/s]
reward: -6.3801, last reward: -7.0310, gradient norm: 120.1: 9%|8 | 56/625 [00:08<01:23, 6.79it/s]
reward: -6.3801, last reward: -7.0310, gradient norm: 120.1: 9%|9 | 57/625 [00:08<01:23, 6.78it/s]
reward: -6.4244, last reward: -6.2039, gradient norm: 15.48: 9%|9 | 57/625 [00:08<01:23, 6.78it/s]
reward: -6.4244, last reward: -6.2039, gradient norm: 15.48: 9%|9 | 58/625 [00:08<01:23, 6.76it/s]
reward: -6.4850, last reward: -6.8748, gradient norm: 4.706: 9%|9 | 58/625 [00:08<01:23, 6.76it/s]
reward: -6.4850, last reward: -6.8748, gradient norm: 4.706: 9%|9 | 59/625 [00:08<01:23, 6.79it/s]
reward: -6.4897, last reward: -5.9210, gradient norm: 11.63: 9%|9 | 59/625 [00:08<01:23, 6.79it/s]
reward: -6.4897, last reward: -5.9210, gradient norm: 11.63: 10%|9 | 60/625 [00:08<01:22, 6.87it/s]
reward: -6.2299, last reward: -7.8964, gradient norm: 13.35: 10%|9 | 60/625 [00:08<01:22, 6.87it/s]
reward: -6.2299, last reward: -7.8964, gradient norm: 13.35: 10%|9 | 61/625 [00:08<01:21, 6.92it/s]
reward: -6.0832, last reward: -9.3934, gradient norm: 4.456: 10%|9 | 61/625 [00:09<01:21, 6.92it/s]
reward: -6.0832, last reward: -9.3934, gradient norm: 4.456: 10%|9 | 62/625 [00:09<01:21, 6.88it/s]
reward: -5.8971, last reward: -10.2933, gradient norm: 10.74: 10%|9 | 62/625 [00:09<01:21, 6.88it/s]
reward: -5.8971, last reward: -10.2933, gradient norm: 10.74: 10%|# | 63/625 [00:09<01:22, 6.85it/s]
reward: -5.3377, last reward: -4.6996, gradient norm: 23.29: 10%|# | 63/625 [00:09<01:22, 6.85it/s]
reward: -5.3377, last reward: -4.6996, gradient norm: 23.29: 10%|# | 64/625 [00:09<01:21, 6.87it/s]
reward: -5.2274, last reward: -2.8916, gradient norm: 4.098: 10%|# | 64/625 [00:09<01:21, 6.87it/s]
reward: -5.2274, last reward: -2.8916, gradient norm: 4.098: 10%|# | 65/625 [00:09<01:21, 6.83it/s]
reward: -5.2660, last reward: -4.9110, gradient norm: 12.28: 10%|# | 65/625 [00:09<01:21, 6.83it/s]
reward: -5.2660, last reward: -4.9110, gradient norm: 12.28: 11%|# | 66/625 [00:09<01:21, 6.88it/s]
reward: -5.4503, last reward: -5.6956, gradient norm: 12.22: 11%|# | 66/625 [00:09<01:21, 6.88it/s]
reward: -5.4503, last reward: -5.6956, gradient norm: 12.22: 11%|# | 67/625 [00:09<01:21, 6.88it/s]
reward: -5.9172, last reward: -5.4026, gradient norm: 7.946: 11%|# | 67/625 [00:09<01:21, 6.88it/s]
reward: -5.9172, last reward: -5.4026, gradient norm: 7.946: 11%|# | 68/625 [00:09<01:20, 6.90it/s]
reward: -5.9229, last reward: -4.5205, gradient norm: 6.294: 11%|# | 68/625 [00:10<01:20, 6.90it/s]
reward: -5.9229, last reward: -4.5205, gradient norm: 6.294: 11%|#1 | 69/625 [00:10<01:21, 6.86it/s]
reward: -5.8872, last reward: -5.6637, gradient norm: 8.019: 11%|#1 | 69/625 [00:10<01:21, 6.86it/s]
reward: -5.8872, last reward: -5.6637, gradient norm: 8.019: 11%|#1 | 70/625 [00:10<01:20, 6.85it/s]
reward: -5.9281, last reward: -4.2082, gradient norm: 5.724: 11%|#1 | 70/625 [00:10<01:20, 6.85it/s]
reward: -5.9281, last reward: -4.2082, gradient norm: 5.724: 11%|#1 | 71/625 [00:10<01:21, 6.82it/s]
reward: -5.8561, last reward: -5.6574, gradient norm: 8.357: 11%|#1 | 71/625 [00:10<01:21, 6.82it/s]
reward: -5.8561, last reward: -5.6574, gradient norm: 8.357: 12%|#1 | 72/625 [00:10<01:21, 6.80it/s]
reward: -5.4138, last reward: -4.5230, gradient norm: 7.385: 12%|#1 | 72/625 [00:10<01:21, 6.80it/s]
reward: -5.4138, last reward: -4.5230, gradient norm: 7.385: 12%|#1 | 73/625 [00:10<01:21, 6.80it/s]
reward: -5.4065, last reward: -5.5642, gradient norm: 9.921: 12%|#1 | 73/625 [00:10<01:21, 6.80it/s]
reward: -5.4065, last reward: -5.5642, gradient norm: 9.921: 12%|#1 | 74/625 [00:10<01:21, 6.79it/s]
reward: -4.9786, last reward: -3.2894, gradient norm: 32.73: 12%|#1 | 74/625 [00:10<01:21, 6.79it/s]
reward: -4.9786, last reward: -3.2894, gradient norm: 32.73: 12%|#2 | 75/625 [00:10<01:21, 6.79it/s]
reward: -5.4129, last reward: -7.5831, gradient norm: 9.266: 12%|#2 | 75/625 [00:11<01:21, 6.79it/s]
reward: -5.4129, last reward: -7.5831, gradient norm: 9.266: 12%|#2 | 76/625 [00:11<01:20, 6.78it/s]
reward: -5.7723, last reward: -7.4152, gradient norm: 5.608: 12%|#2 | 76/625 [00:11<01:20, 6.78it/s]
reward: -5.7723, last reward: -7.4152, gradient norm: 5.608: 12%|#2 | 77/625 [00:11<01:20, 6.79it/s]
reward: -6.1604, last reward: -8.0898, gradient norm: 4.389: 12%|#2 | 77/625 [00:11<01:20, 6.79it/s]
reward: -6.1604, last reward: -8.0898, gradient norm: 4.389: 12%|#2 | 78/625 [00:11<01:20, 6.78it/s]
reward: -6.5155, last reward: -5.5376, gradient norm: 36.34: 12%|#2 | 78/625 [00:11<01:20, 6.78it/s]
reward: -6.5155, last reward: -5.5376, gradient norm: 36.34: 13%|#2 | 79/625 [00:11<01:20, 6.79it/s]
reward: -6.5616, last reward: -6.4094, gradient norm: 8.283: 13%|#2 | 79/625 [00:11<01:20, 6.79it/s]
reward: -6.5616, last reward: -6.4094, gradient norm: 8.283: 13%|#2 | 80/625 [00:11<01:20, 6.78it/s]
reward: -6.5333, last reward: -7.4803, gradient norm: 5.895: 13%|#2 | 80/625 [00:11<01:20, 6.78it/s]
reward: -6.5333, last reward: -7.4803, gradient norm: 5.895: 13%|#2 | 81/625 [00:11<01:20, 6.77it/s]
reward: -6.6566, last reward: -5.2588, gradient norm: 7.662: 13%|#2 | 81/625 [00:11<01:20, 6.77it/s]
reward: -6.6566, last reward: -5.2588, gradient norm: 7.662: 13%|#3 | 82/625 [00:11<01:20, 6.77it/s]
reward: -6.4732, last reward: -6.7503, gradient norm: 6.068: 13%|#3 | 82/625 [00:12<01:20, 6.77it/s]
reward: -6.4732, last reward: -6.7503, gradient norm: 6.068: 13%|#3 | 83/625 [00:12<01:20, 6.77it/s]
reward: -6.0714, last reward: -7.3370, gradient norm: 8.059: 13%|#3 | 83/625 [00:12<01:20, 6.77it/s]
reward: -6.0714, last reward: -7.3370, gradient norm: 8.059: 13%|#3 | 84/625 [00:12<01:19, 6.78it/s]
reward: -5.8612, last reward: -6.1915, gradient norm: 9.3: 13%|#3 | 84/625 [00:12<01:19, 6.78it/s]
reward: -5.8612, last reward: -6.1915, gradient norm: 9.3: 14%|#3 | 85/625 [00:12<01:19, 6.77it/s]
reward: -5.3855, last reward: -5.0349, gradient norm: 15.2: 14%|#3 | 85/625 [00:12<01:19, 6.77it/s]
reward: -5.3855, last reward: -5.0349, gradient norm: 15.2: 14%|#3 | 86/625 [00:12<01:19, 6.77it/s]
reward: -4.9644, last reward: -3.4538, gradient norm: 3.445: 14%|#3 | 86/625 [00:12<01:19, 6.77it/s]
reward: -4.9644, last reward: -3.4538, gradient norm: 3.445: 14%|#3 | 87/625 [00:12<01:19, 6.77it/s]
reward: -5.0392, last reward: -4.4080, gradient norm: 11.45: 14%|#3 | 87/625 [00:12<01:19, 6.77it/s]
reward: -5.0392, last reward: -4.4080, gradient norm: 11.45: 14%|#4 | 88/625 [00:12<01:18, 6.80it/s]
reward: -5.1648, last reward: -5.9599, gradient norm: 143.4: 14%|#4 | 88/625 [00:12<01:18, 6.80it/s]
reward: -5.1648, last reward: -5.9599, gradient norm: 143.4: 14%|#4 | 89/625 [00:12<01:18, 6.83it/s]
reward: -5.4284, last reward: -5.5946, gradient norm: 10.3: 14%|#4 | 89/625 [00:13<01:18, 6.83it/s]
reward: -5.4284, last reward: -5.5946, gradient norm: 10.3: 14%|#4 | 90/625 [00:13<01:18, 6.84it/s]
reward: -5.2590, last reward: -5.9181, gradient norm: 11.15: 14%|#4 | 90/625 [00:13<01:18, 6.84it/s]
reward: -5.2590, last reward: -5.9181, gradient norm: 11.15: 15%|#4 | 91/625 [00:13<01:17, 6.85it/s]
reward: -5.4621, last reward: -5.9075, gradient norm: 8.674: 15%|#4 | 91/625 [00:13<01:17, 6.85it/s]
reward: -5.4621, last reward: -5.9075, gradient norm: 8.674: 15%|#4 | 92/625 [00:13<01:17, 6.87it/s]
reward: -5.1772, last reward: -4.9444, gradient norm: 8.351: 15%|#4 | 92/625 [00:13<01:17, 6.87it/s]
reward: -5.1772, last reward: -4.9444, gradient norm: 8.351: 15%|#4 | 93/625 [00:13<01:17, 6.86it/s]
reward: -4.9391, last reward: -4.5595, gradient norm: 8.1: 15%|#4 | 93/625 [00:13<01:17, 6.86it/s]
reward: -4.9391, last reward: -4.5595, gradient norm: 8.1: 15%|#5 | 94/625 [00:13<01:17, 6.88it/s]
reward: -4.8673, last reward: -4.6240, gradient norm: 14.43: 15%|#5 | 94/625 [00:13<01:17, 6.88it/s]
reward: -4.8673, last reward: -4.6240, gradient norm: 14.43: 15%|#5 | 95/625 [00:13<01:17, 6.87it/s]
reward: -4.5919, last reward: -5.0018, gradient norm: 26.09: 15%|#5 | 95/625 [00:13<01:17, 6.87it/s]
reward: -4.5919, last reward: -5.0018, gradient norm: 26.09: 15%|#5 | 96/625 [00:13<01:16, 6.92it/s]
reward: -5.1071, last reward: -3.9127, gradient norm: 2.251: 15%|#5 | 96/625 [00:14<01:16, 6.92it/s]
reward: -5.1071, last reward: -3.9127, gradient norm: 2.251: 16%|#5 | 97/625 [00:14<01:16, 6.90it/s]
reward: -4.9799, last reward: -5.3131, gradient norm: 19.65: 16%|#5 | 97/625 [00:14<01:16, 6.90it/s]
reward: -4.9799, last reward: -5.3131, gradient norm: 19.65: 16%|#5 | 98/625 [00:14<01:16, 6.88it/s]
reward: -4.9612, last reward: -3.9705, gradient norm: 12.55: 16%|#5 | 98/625 [00:14<01:16, 6.88it/s]
reward: -4.9612, last reward: -3.9705, gradient norm: 12.55: 16%|#5 | 99/625 [00:14<01:16, 6.84it/s]
reward: -4.8741, last reward: -4.2230, gradient norm: 6.19: 16%|#5 | 99/625 [00:14<01:16, 6.84it/s]
reward: -4.8741, last reward: -4.2230, gradient norm: 6.19: 16%|#6 | 100/625 [00:14<01:16, 6.82it/s]
reward: -5.0972, last reward: -5.0337, gradient norm: 11.86: 16%|#6 | 100/625 [00:14<01:16, 6.82it/s]
reward: -5.0972, last reward: -5.0337, gradient norm: 11.86: 16%|#6 | 101/625 [00:14<01:16, 6.82it/s]
reward: -5.0350, last reward: -5.0654, gradient norm: 10.83: 16%|#6 | 101/625 [00:14<01:16, 6.82it/s]
reward: -5.0350, last reward: -5.0654, gradient norm: 10.83: 16%|#6 | 102/625 [00:14<01:16, 6.82it/s]
reward: -5.2441, last reward: -4.4596, gradient norm: 7.362: 16%|#6 | 102/625 [00:15<01:16, 6.82it/s]
reward: -5.2441, last reward: -4.4596, gradient norm: 7.362: 16%|#6 | 103/625 [00:15<01:16, 6.81it/s]
reward: -5.1664, last reward: -5.4362, gradient norm: 8.171: 16%|#6 | 103/625 [00:15<01:16, 6.81it/s]
reward: -5.1664, last reward: -5.4362, gradient norm: 8.171: 17%|#6 | 104/625 [00:15<01:16, 6.80it/s]
reward: -5.4041, last reward: -5.6907, gradient norm: 7.77: 17%|#6 | 104/625 [00:15<01:16, 6.80it/s]
reward: -5.4041, last reward: -5.6907, gradient norm: 7.77: 17%|#6 | 105/625 [00:15<01:15, 6.84it/s]
reward: -5.4664, last reward: -6.2760, gradient norm: 11.19: 17%|#6 | 105/625 [00:15<01:15, 6.84it/s]
reward: -5.4664, last reward: -6.2760, gradient norm: 11.19: 17%|#6 | 106/625 [00:15<01:15, 6.84it/s]
reward: -5.0299, last reward: -3.9712, gradient norm: 9.349: 17%|#6 | 106/625 [00:15<01:15, 6.84it/s]
reward: -5.0299, last reward: -3.9712, gradient norm: 9.349: 17%|#7 | 107/625 [00:15<01:15, 6.86it/s]
reward: -4.3332, last reward: -2.4479, gradient norm: 5.772: 17%|#7 | 107/625 [00:15<01:15, 6.86it/s]
reward: -4.3332, last reward: -2.4479, gradient norm: 5.772: 17%|#7 | 108/625 [00:15<01:15, 6.88it/s]
reward: -4.4357, last reward: -2.9591, gradient norm: 4.543: 17%|#7 | 108/625 [00:15<01:15, 6.88it/s]
reward: -4.4357, last reward: -2.9591, gradient norm: 4.543: 17%|#7 | 109/625 [00:15<01:14, 6.88it/s]
reward: -4.6216, last reward: -3.1353, gradient norm: 4.692: 17%|#7 | 109/625 [00:16<01:14, 6.88it/s]
reward: -4.6216, last reward: -3.1353, gradient norm: 4.692: 18%|#7 | 110/625 [00:16<01:14, 6.89it/s]
reward: -4.6261, last reward: -3.7086, gradient norm: 4.496: 18%|#7 | 110/625 [00:16<01:14, 6.89it/s]
reward: -4.6261, last reward: -3.7086, gradient norm: 4.496: 18%|#7 | 111/625 [00:16<01:14, 6.89it/s]
reward: -4.7758, last reward: -5.9818, gradient norm: 21.71: 18%|#7 | 111/625 [00:16<01:14, 6.89it/s]
reward: -4.7758, last reward: -5.9818, gradient norm: 21.71: 18%|#7 | 112/625 [00:16<01:13, 6.94it/s]
reward: -4.7772, last reward: -7.5055, gradient norm: 62.86: 18%|#7 | 112/625 [00:16<01:13, 6.94it/s]
reward: -4.7772, last reward: -7.5055, gradient norm: 62.86: 18%|#8 | 113/625 [00:16<01:13, 6.92it/s]
reward: -4.5840, last reward: -5.3180, gradient norm: 18.74: 18%|#8 | 113/625 [00:16<01:13, 6.92it/s]
reward: -4.5840, last reward: -5.3180, gradient norm: 18.74: 18%|#8 | 114/625 [00:16<01:13, 6.93it/s]
reward: -4.2976, last reward: -3.2083, gradient norm: 10.63: 18%|#8 | 114/625 [00:16<01:13, 6.93it/s]
reward: -4.2976, last reward: -3.2083, gradient norm: 10.63: 18%|#8 | 115/625 [00:16<01:14, 6.82it/s]
reward: -4.5275, last reward: -3.6873, gradient norm: 15.65: 18%|#8 | 115/625 [00:16<01:14, 6.82it/s]
reward: -4.5275, last reward: -3.6873, gradient norm: 15.65: 19%|#8 | 116/625 [00:16<01:14, 6.87it/s]
reward: -4.4107, last reward: -3.1624, gradient norm: 19.7: 19%|#8 | 116/625 [00:17<01:14, 6.87it/s]
reward: -4.4107, last reward: -3.1624, gradient norm: 19.7: 19%|#8 | 117/625 [00:17<01:14, 6.85it/s]
reward: -4.6372, last reward: -3.2571, gradient norm: 15.83: 19%|#8 | 117/625 [00:17<01:14, 6.85it/s]
reward: -4.6372, last reward: -3.2571, gradient norm: 15.83: 19%|#8 | 118/625 [00:17<01:13, 6.87it/s]
reward: -4.4039, last reward: -4.4428, gradient norm: 13.06: 19%|#8 | 118/625 [00:17<01:13, 6.87it/s]
reward: -4.4039, last reward: -4.4428, gradient norm: 13.06: 19%|#9 | 119/625 [00:17<01:13, 6.91it/s]
reward: -4.4728, last reward: -3.5628, gradient norm: 12.04: 19%|#9 | 119/625 [00:17<01:13, 6.91it/s]
reward: -4.4728, last reward: -3.5628, gradient norm: 12.04: 19%|#9 | 120/625 [00:17<01:12, 6.92it/s]
reward: -4.6767, last reward: -5.2466, gradient norm: 6.522: 19%|#9 | 120/625 [00:17<01:12, 6.92it/s]
reward: -4.6767, last reward: -5.2466, gradient norm: 6.522: 19%|#9 | 121/625 [00:17<01:12, 6.91it/s]
reward: -4.5873, last reward: -6.5072, gradient norm: 19.21: 19%|#9 | 121/625 [00:17<01:12, 6.91it/s]
reward: -4.5873, last reward: -6.5072, gradient norm: 19.21: 20%|#9 | 122/625 [00:17<01:12, 6.94it/s]
reward: -4.6548, last reward: -6.3766, gradient norm: 5.692: 20%|#9 | 122/625 [00:17<01:12, 6.94it/s]
reward: -4.6548, last reward: -6.3766, gradient norm: 5.692: 20%|#9 | 123/625 [00:17<01:12, 6.97it/s]
reward: -4.5134, last reward: -7.1955, gradient norm: 11.11: 20%|#9 | 123/625 [00:18<01:12, 6.97it/s]
reward: -4.5134, last reward: -7.1955, gradient norm: 11.11: 20%|#9 | 124/625 [00:18<01:12, 6.91it/s]
reward: -4.2481, last reward: -7.0591, gradient norm: 11.85: 20%|#9 | 124/625 [00:18<01:12, 6.91it/s]
reward: -4.2481, last reward: -7.0591, gradient norm: 11.85: 20%|## | 125/625 [00:18<01:12, 6.94it/s]
reward: -4.4500, last reward: -5.3368, gradient norm: 10.19: 20%|## | 125/625 [00:18<01:12, 6.94it/s]
reward: -4.4500, last reward: -5.3368, gradient norm: 10.19: 20%|## | 126/625 [00:18<01:12, 6.91it/s]
reward: -3.9708, last reward: -2.7059, gradient norm: 42.81: 20%|## | 126/625 [00:18<01:12, 6.91it/s]
reward: -3.9708, last reward: -2.7059, gradient norm: 42.81: 20%|## | 127/625 [00:18<01:12, 6.91it/s]
reward: -4.3031, last reward: -3.2534, gradient norm: 4.843: 20%|## | 127/625 [00:18<01:12, 6.91it/s]
reward: -4.3031, last reward: -3.2534, gradient norm: 4.843: 20%|## | 128/625 [00:18<01:12, 6.90it/s]
reward: -4.3327, last reward: -4.6193, gradient norm: 20.96: 20%|## | 128/625 [00:18<01:12, 6.90it/s]
reward: -4.3327, last reward: -4.6193, gradient norm: 20.96: 21%|## | 129/625 [00:18<01:11, 6.93it/s]
reward: -4.4831, last reward: -4.1172, gradient norm: 24.81: 21%|## | 129/625 [00:18<01:11, 6.93it/s]
reward: -4.4831, last reward: -4.1172, gradient norm: 24.81: 21%|## | 130/625 [00:18<01:11, 6.91it/s]
reward: -4.2593, last reward: -4.4219, gradient norm: 5.962: 21%|## | 130/625 [00:19<01:11, 6.91it/s]
reward: -4.2593, last reward: -4.4219, gradient norm: 5.962: 21%|## | 131/625 [00:19<01:11, 6.90it/s]
reward: -4.4800, last reward: -3.8380, gradient norm: 2.899: 21%|## | 131/625 [00:19<01:11, 6.90it/s]
reward: -4.4800, last reward: -3.8380, gradient norm: 2.899: 21%|##1 | 132/625 [00:19<01:11, 6.86it/s]
reward: -4.2721, last reward: -4.9048, gradient norm: 7.166: 21%|##1 | 132/625 [00:19<01:11, 6.86it/s]
reward: -4.2721, last reward: -4.9048, gradient norm: 7.166: 21%|##1 | 133/625 [00:19<01:12, 6.83it/s]
reward: -4.2419, last reward: -4.5248, gradient norm: 25.93: 21%|##1 | 133/625 [00:19<01:12, 6.83it/s]
reward: -4.2419, last reward: -4.5248, gradient norm: 25.93: 21%|##1 | 134/625 [00:19<01:11, 6.82it/s]
reward: -4.2139, last reward: -4.4278, gradient norm: 20.26: 21%|##1 | 134/625 [00:19<01:11, 6.82it/s]
reward: -4.2139, last reward: -4.4278, gradient norm: 20.26: 22%|##1 | 135/625 [00:19<01:11, 6.87it/s]
reward: -4.0690, last reward: -2.5140, gradient norm: 22.5: 22%|##1 | 135/625 [00:19<01:11, 6.87it/s]
reward: -4.0690, last reward: -2.5140, gradient norm: 22.5: 22%|##1 | 136/625 [00:19<01:11, 6.87it/s]
reward: -4.1140, last reward: -3.7402, gradient norm: 11.11: 22%|##1 | 136/625 [00:19<01:11, 6.87it/s]
reward: -4.1140, last reward: -3.7402, gradient norm: 11.11: 22%|##1 | 137/625 [00:19<01:10, 6.87it/s]
reward: -4.5356, last reward: -5.1636, gradient norm: 400.1: 22%|##1 | 137/625 [00:20<01:10, 6.87it/s]
reward: -4.5356, last reward: -5.1636, gradient norm: 400.1: 22%|##2 | 138/625 [00:20<01:10, 6.89it/s]
reward: -5.0671, last reward: -5.8798, gradient norm: 13.34: 22%|##2 | 138/625 [00:20<01:10, 6.89it/s]
reward: -5.0671, last reward: -5.8798, gradient norm: 13.34: 22%|##2 | 139/625 [00:20<01:10, 6.89it/s]
reward: -4.8918, last reward: -6.3298, gradient norm: 7.307: 22%|##2 | 139/625 [00:20<01:10, 6.89it/s]
reward: -4.8918, last reward: -6.3298, gradient norm: 7.307: 22%|##2 | 140/625 [00:20<01:10, 6.92it/s]
reward: -5.1779, last reward: -4.1915, gradient norm: 11.43: 22%|##2 | 140/625 [00:20<01:10, 6.92it/s]
reward: -5.1779, last reward: -4.1915, gradient norm: 11.43: 23%|##2 | 141/625 [00:20<01:10, 6.90it/s]
reward: -5.1771, last reward: -4.3624, gradient norm: 6.936: 23%|##2 | 141/625 [00:20<01:10, 6.90it/s]
reward: -5.1771, last reward: -4.3624, gradient norm: 6.936: 23%|##2 | 142/625 [00:20<01:09, 6.94it/s]
reward: -5.1683, last reward: -3.4810, gradient norm: 13.29: 23%|##2 | 142/625 [00:20<01:09, 6.94it/s]
reward: -5.1683, last reward: -3.4810, gradient norm: 13.29: 23%|##2 | 143/625 [00:20<01:09, 6.96it/s]
reward: -4.9373, last reward: -5.4435, gradient norm: 19.33: 23%|##2 | 143/625 [00:20<01:09, 6.96it/s]
reward: -4.9373, last reward: -5.4435, gradient norm: 19.33: 23%|##3 | 144/625 [00:20<01:08, 6.98it/s]
reward: -4.4396, last reward: -4.8092, gradient norm: 118.9: 23%|##3 | 144/625 [00:21<01:08, 6.98it/s]
reward: -4.4396, last reward: -4.8092, gradient norm: 118.9: 23%|##3 | 145/625 [00:21<01:08, 7.00it/s]
reward: -4.3911, last reward: -8.2572, gradient norm: 15.04: 23%|##3 | 145/625 [00:21<01:08, 7.00it/s]
reward: -4.3911, last reward: -8.2572, gradient norm: 15.04: 23%|##3 | 146/625 [00:21<01:08, 7.00it/s]
reward: -4.4212, last reward: -3.0260, gradient norm: 26.01: 23%|##3 | 146/625 [00:21<01:08, 7.00it/s]
reward: -4.4212, last reward: -3.0260, gradient norm: 26.01: 24%|##3 | 147/625 [00:21<01:08, 6.93it/s]
reward: -4.0939, last reward: -4.6478, gradient norm: 9.605: 24%|##3 | 147/625 [00:21<01:08, 6.93it/s]
reward: -4.0939, last reward: -4.6478, gradient norm: 9.605: 24%|##3 | 148/625 [00:21<01:09, 6.89it/s]
reward: -4.6606, last reward: -4.7289, gradient norm: 11.19: 24%|##3 | 148/625 [00:21<01:09, 6.89it/s]
reward: -4.6606, last reward: -4.7289, gradient norm: 11.19: 24%|##3 | 149/625 [00:21<01:08, 6.91it/s]
reward: -4.9300, last reward: -4.7193, gradient norm: 8.563: 24%|##3 | 149/625 [00:21<01:08, 6.91it/s]
reward: -4.9300, last reward: -4.7193, gradient norm: 8.563: 24%|##4 | 150/625 [00:21<01:08, 6.93it/s]
reward: -5.1166, last reward: -4.8514, gradient norm: 8.384: 24%|##4 | 150/625 [00:21<01:08, 6.93it/s]
reward: -5.1166, last reward: -4.8514, gradient norm: 8.384: 24%|##4 | 151/625 [00:21<01:08, 6.95it/s]
reward: -4.9108, last reward: -5.0672, gradient norm: 9.292: 24%|##4 | 151/625 [00:22<01:08, 6.95it/s]
reward: -4.9108, last reward: -5.0672, gradient norm: 9.292: 24%|##4 | 152/625 [00:22<01:08, 6.93it/s]
reward: -4.8591, last reward: -4.3768, gradient norm: 9.72: 24%|##4 | 152/625 [00:22<01:08, 6.93it/s]
reward: -4.8591, last reward: -4.3768, gradient norm: 9.72: 24%|##4 | 153/625 [00:22<01:08, 6.94it/s]
reward: -4.2721, last reward: -3.9976, gradient norm: 10.37: 24%|##4 | 153/625 [00:22<01:08, 6.94it/s]
reward: -4.2721, last reward: -3.9976, gradient norm: 10.37: 25%|##4 | 154/625 [00:22<01:07, 6.97it/s]
reward: -4.0576, last reward: -2.0067, gradient norm: 8.935: 25%|##4 | 154/625 [00:22<01:07, 6.97it/s]
reward: -4.0576, last reward: -2.0067, gradient norm: 8.935: 25%|##4 | 155/625 [00:22<01:07, 6.99it/s]
reward: -4.4199, last reward: -5.1722, gradient norm: 18.7: 25%|##4 | 155/625 [00:22<01:07, 6.99it/s]
reward: -4.4199, last reward: -5.1722, gradient norm: 18.7: 25%|##4 | 156/625 [00:22<01:06, 7.01it/s]
reward: -4.8310, last reward: -7.3466, gradient norm: 28.52: 25%|##4 | 156/625 [00:22<01:06, 7.01it/s]
reward: -4.8310, last reward: -7.3466, gradient norm: 28.52: 25%|##5 | 157/625 [00:22<01:06, 7.02it/s]
reward: -4.8631, last reward: -6.2492, gradient norm: 89.17: 25%|##5 | 157/625 [00:22<01:06, 7.02it/s]
reward: -4.8631, last reward: -6.2492, gradient norm: 89.17: 25%|##5 | 158/625 [00:22<01:06, 7.03it/s]
reward: -4.8763, last reward: -6.1277, gradient norm: 24.43: 25%|##5 | 158/625 [00:23<01:06, 7.03it/s]
reward: -4.8763, last reward: -6.1277, gradient norm: 24.43: 25%|##5 | 159/625 [00:23<01:06, 7.04it/s]
reward: -4.5562, last reward: -5.7446, gradient norm: 23.35: 25%|##5 | 159/625 [00:23<01:06, 7.04it/s]
reward: -4.5562, last reward: -5.7446, gradient norm: 23.35: 26%|##5 | 160/625 [00:23<01:06, 7.02it/s]
reward: -4.1082, last reward: -4.9830, gradient norm: 22.14: 26%|##5 | 160/625 [00:23<01:06, 7.02it/s]
reward: -4.1082, last reward: -4.9830, gradient norm: 22.14: 26%|##5 | 161/625 [00:23<01:06, 6.97it/s]
reward: -4.0946, last reward: -2.5229, gradient norm: 10.47: 26%|##5 | 161/625 [00:23<01:06, 6.97it/s]
reward: -4.0946, last reward: -2.5229, gradient norm: 10.47: 26%|##5 | 162/625 [00:23<01:06, 7.00it/s]
reward: -4.4574, last reward: -4.6900, gradient norm: 112.6: 26%|##5 | 162/625 [00:23<01:06, 7.00it/s]
reward: -4.4574, last reward: -4.6900, gradient norm: 112.6: 26%|##6 | 163/625 [00:23<01:05, 7.01it/s]
reward: -5.2229, last reward: -4.0318, gradient norm: 6.482: 26%|##6 | 163/625 [00:23<01:05, 7.01it/s]
reward: -5.2229, last reward: -4.0318, gradient norm: 6.482: 26%|##6 | 164/625 [00:23<01:05, 7.00it/s]
reward: -5.0543, last reward: -4.0817, gradient norm: 5.761: 26%|##6 | 164/625 [00:23<01:05, 7.00it/s]
reward: -5.0543, last reward: -4.0817, gradient norm: 5.761: 26%|##6 | 165/625 [00:23<01:06, 6.95it/s]
reward: -5.2809, last reward: -4.5118, gradient norm: 5.366: 26%|##6 | 165/625 [00:24<01:06, 6.95it/s]
reward: -5.2809, last reward: -4.5118, gradient norm: 5.366: 27%|##6 | 166/625 [00:24<01:05, 6.98it/s]
reward: -5.1142, last reward: -4.5635, gradient norm: 5.04: 27%|##6 | 166/625 [00:24<01:05, 6.98it/s]
reward: -5.1142, last reward: -4.5635, gradient norm: 5.04: 27%|##6 | 167/625 [00:24<01:05, 6.99it/s]
reward: -5.1949, last reward: -4.2327, gradient norm: 4.982: 27%|##6 | 167/625 [00:24<01:05, 6.99it/s]
reward: -5.1949, last reward: -4.2327, gradient norm: 4.982: 27%|##6 | 168/625 [00:24<01:05, 7.00it/s]
reward: -5.0967, last reward: -5.0387, gradient norm: 7.457: 27%|##6 | 168/625 [00:24<01:05, 7.00it/s]
reward: -5.0967, last reward: -5.0387, gradient norm: 7.457: 27%|##7 | 169/625 [00:24<01:05, 7.01it/s]
reward: -5.0782, last reward: -5.2150, gradient norm: 10.54: 27%|##7 | 169/625 [00:24<01:05, 7.01it/s]
reward: -5.0782, last reward: -5.2150, gradient norm: 10.54: 27%|##7 | 170/625 [00:24<01:04, 7.02it/s]
reward: -4.5222, last reward: -4.3725, gradient norm: 22.63: 27%|##7 | 170/625 [00:24<01:04, 7.02it/s]
reward: -4.5222, last reward: -4.3725, gradient norm: 22.63: 27%|##7 | 171/625 [00:24<01:05, 6.94it/s]
reward: -3.9288, last reward: -3.9837, gradient norm: 83.59: 27%|##7 | 171/625 [00:24<01:05, 6.94it/s]
reward: -3.9288, last reward: -3.9837, gradient norm: 83.59: 28%|##7 | 172/625 [00:24<01:05, 6.88it/s]
reward: -4.1416, last reward: -4.1099, gradient norm: 30.57: 28%|##7 | 172/625 [00:25<01:05, 6.88it/s]
reward: -4.1416, last reward: -4.1099, gradient norm: 30.57: 28%|##7 | 173/625 [00:25<01:06, 6.84it/s]
reward: -4.8620, last reward: -6.8475, gradient norm: 18.91: 28%|##7 | 173/625 [00:25<01:06, 6.84it/s]
reward: -4.8620, last reward: -6.8475, gradient norm: 18.91: 28%|##7 | 174/625 [00:25<01:06, 6.82it/s]
reward: -5.1807, last reward: -6.4375, gradient norm: 18.48: 28%|##7 | 174/625 [00:25<01:06, 6.82it/s]
reward: -5.1807, last reward: -6.4375, gradient norm: 18.48: 28%|##8 | 175/625 [00:25<01:06, 6.80it/s]
reward: -5.1148, last reward: -5.0645, gradient norm: 14.36: 28%|##8 | 175/625 [00:25<01:06, 6.80it/s]
reward: -5.1148, last reward: -5.0645, gradient norm: 14.36: 28%|##8 | 176/625 [00:25<01:06, 6.78it/s]
reward: -5.2751, last reward: -4.8313, gradient norm: 15.32: 28%|##8 | 176/625 [00:25<01:06, 6.78it/s]
reward: -5.2751, last reward: -4.8313, gradient norm: 15.32: 28%|##8 | 177/625 [00:25<01:06, 6.77it/s]
reward: -4.9286, last reward: -6.9770, gradient norm: 24.75: 28%|##8 | 177/625 [00:25<01:06, 6.77it/s]
reward: -4.9286, last reward: -6.9770, gradient norm: 24.75: 28%|##8 | 178/625 [00:25<01:06, 6.77it/s]
reward: -4.5735, last reward: -5.2837, gradient norm: 15.2: 28%|##8 | 178/625 [00:26<01:06, 6.77it/s]
reward: -4.5735, last reward: -5.2837, gradient norm: 15.2: 29%|##8 | 179/625 [00:26<01:05, 6.76it/s]
reward: -4.2926, last reward: -1.9489, gradient norm: 18.24: 29%|##8 | 179/625 [00:26<01:05, 6.76it/s]
reward: -4.2926, last reward: -1.9489, gradient norm: 18.24: 29%|##8 | 180/625 [00:26<01:05, 6.77it/s]
reward: -4.1507, last reward: -3.5593, gradient norm: 37.66: 29%|##8 | 180/625 [00:26<01:05, 6.77it/s]
reward: -4.1507, last reward: -3.5593, gradient norm: 37.66: 29%|##8 | 181/625 [00:26<01:05, 6.77it/s]
reward: -3.8724, last reward: -4.3567, gradient norm: 16.67: 29%|##8 | 181/625 [00:26<01:05, 6.77it/s]
reward: -3.8724, last reward: -4.3567, gradient norm: 16.67: 29%|##9 | 182/625 [00:26<01:05, 6.76it/s]
reward: -4.3574, last reward: -3.6140, gradient norm: 13.96: 29%|##9 | 182/625 [00:26<01:05, 6.76it/s]
reward: -4.3574, last reward: -3.6140, gradient norm: 13.96: 29%|##9 | 183/625 [00:26<01:05, 6.77it/s]
reward: -4.7895, last reward: -6.2518, gradient norm: 14.74: 29%|##9 | 183/625 [00:26<01:05, 6.77it/s]
reward: -4.7895, last reward: -6.2518, gradient norm: 14.74: 29%|##9 | 184/625 [00:26<01:05, 6.76it/s]
reward: -4.6146, last reward: -5.6969, gradient norm: 11.45: 29%|##9 | 184/625 [00:26<01:05, 6.76it/s]
reward: -4.6146, last reward: -5.6969, gradient norm: 11.45: 30%|##9 | 185/625 [00:26<01:05, 6.76it/s]
reward: -4.8776, last reward: -5.7358, gradient norm: 13.16: 30%|##9 | 185/625 [00:27<01:05, 6.76it/s]
reward: -4.8776, last reward: -5.7358, gradient norm: 13.16: 30%|##9 | 186/625 [00:27<01:05, 6.75it/s]
reward: -4.3722, last reward: -4.8428, gradient norm: 23.57: 30%|##9 | 186/625 [00:27<01:05, 6.75it/s]
reward: -4.3722, last reward: -4.8428, gradient norm: 23.57: 30%|##9 | 187/625 [00:27<01:04, 6.76it/s]
reward: -4.2656, last reward: -3.7955, gradient norm: 54.67: 30%|##9 | 187/625 [00:27<01:04, 6.76it/s]
reward: -4.2656, last reward: -3.7955, gradient norm: 54.67: 30%|### | 188/625 [00:27<01:04, 6.76it/s]
reward: -4.0092, last reward: -1.7106, gradient norm: 7.829: 30%|### | 188/625 [00:27<01:04, 6.76it/s]
reward: -4.0092, last reward: -1.7106, gradient norm: 7.829: 30%|### | 189/625 [00:27<01:04, 6.77it/s]
reward: -4.2264, last reward: -3.6919, gradient norm: 16.17: 30%|### | 189/625 [00:27<01:04, 6.77it/s]
reward: -4.2264, last reward: -3.6919, gradient norm: 16.17: 30%|### | 190/625 [00:27<01:04, 6.76it/s]
reward: -4.1438, last reward: -2.1362, gradient norm: 19.43: 30%|### | 190/625 [00:27<01:04, 6.76it/s]
reward: -4.1438, last reward: -2.1362, gradient norm: 19.43: 31%|### | 191/625 [00:27<01:04, 6.76it/s]
reward: -4.0618, last reward: -2.8217, gradient norm: 73.63: 31%|### | 191/625 [00:27<01:04, 6.76it/s]
reward: -4.0618, last reward: -2.8217, gradient norm: 73.63: 31%|### | 192/625 [00:27<01:04, 6.76it/s]
reward: -3.9420, last reward: -3.6765, gradient norm: 34.1: 31%|### | 192/625 [00:28<01:04, 6.76it/s]
reward: -3.9420, last reward: -3.6765, gradient norm: 34.1: 31%|### | 193/625 [00:28<01:03, 6.76it/s]
reward: -3.7745, last reward: -4.0709, gradient norm: 26.48: 31%|### | 193/625 [00:28<01:03, 6.76it/s]
reward: -3.7745, last reward: -4.0709, gradient norm: 26.48: 31%|###1 | 194/625 [00:28<01:03, 6.76it/s]
reward: -3.9478, last reward: -2.6867, gradient norm: 22.82: 31%|###1 | 194/625 [00:28<01:03, 6.76it/s]
reward: -3.9478, last reward: -2.6867, gradient norm: 22.82: 31%|###1 | 195/625 [00:28<01:03, 6.75it/s]
reward: -3.6507, last reward: -2.6225, gradient norm: 37.44: 31%|###1 | 195/625 [00:28<01:03, 6.75it/s]
reward: -3.6507, last reward: -2.6225, gradient norm: 37.44: 31%|###1 | 196/625 [00:28<01:03, 6.75it/s]
reward: -4.2244, last reward: -3.2195, gradient norm: 10.71: 31%|###1 | 196/625 [00:28<01:03, 6.75it/s]
reward: -4.2244, last reward: -3.2195, gradient norm: 10.71: 32%|###1 | 197/625 [00:28<01:03, 6.75it/s]
reward: -4.5385, last reward: -3.9263, gradient norm: 31.03: 32%|###1 | 197/625 [00:28<01:03, 6.75it/s]
reward: -4.5385, last reward: -3.9263, gradient norm: 31.03: 32%|###1 | 198/625 [00:28<01:03, 6.74it/s]
reward: -4.1878, last reward: -3.2374, gradient norm: 34.35: 32%|###1 | 198/625 [00:28<01:03, 6.74it/s]
reward: -4.1878, last reward: -3.2374, gradient norm: 34.35: 32%|###1 | 199/625 [00:28<01:03, 6.71it/s]
reward: -3.8054, last reward: -2.3504, gradient norm: 5.557: 32%|###1 | 199/625 [00:29<01:03, 6.71it/s]
reward: -3.8054, last reward: -2.3504, gradient norm: 5.557: 32%|###2 | 200/625 [00:29<01:03, 6.71it/s]
reward: -4.0766, last reward: -4.6825, gradient norm: 38.72: 32%|###2 | 200/625 [00:29<01:03, 6.71it/s]
reward: -4.0766, last reward: -4.6825, gradient norm: 38.72: 32%|###2 | 201/625 [00:29<01:03, 6.72it/s]
reward: -4.2011, last reward: -5.8393, gradient norm: 21.06: 32%|###2 | 201/625 [00:29<01:03, 6.72it/s]
reward: -4.2011, last reward: -5.8393, gradient norm: 21.06: 32%|###2 | 202/625 [00:29<01:02, 6.73it/s]
reward: -4.0803, last reward: -3.7815, gradient norm: 10.6: 32%|###2 | 202/625 [00:29<01:02, 6.73it/s]
reward: -4.0803, last reward: -3.7815, gradient norm: 10.6: 32%|###2 | 203/625 [00:29<01:02, 6.74it/s]
reward: -3.8363, last reward: -3.2460, gradient norm: 32.57: 32%|###2 | 203/625 [00:29<01:02, 6.74it/s]
reward: -3.8363, last reward: -3.2460, gradient norm: 32.57: 33%|###2 | 204/625 [00:29<01:02, 6.76it/s]
reward: -3.8643, last reward: -3.2191, gradient norm: 8.593: 33%|###2 | 204/625 [00:29<01:02, 6.76it/s]
reward: -3.8643, last reward: -3.2191, gradient norm: 8.593: 33%|###2 | 205/625 [00:29<01:02, 6.75it/s]
reward: -4.0773, last reward: -5.1343, gradient norm: 14.49: 33%|###2 | 205/625 [00:30<01:02, 6.75it/s]
reward: -4.0773, last reward: -5.1343, gradient norm: 14.49: 33%|###2 | 206/625 [00:30<01:01, 6.77it/s]
reward: -4.1400, last reward: -5.8657, gradient norm: 17.05: 33%|###2 | 206/625 [00:30<01:01, 6.77it/s]
reward: -4.1400, last reward: -5.8657, gradient norm: 17.05: 33%|###3 | 207/625 [00:30<01:01, 6.78it/s]
reward: -3.9304, last reward: -2.7584, gradient norm: 33.25: 33%|###3 | 207/625 [00:30<01:01, 6.78it/s]
reward: -3.9304, last reward: -2.7584, gradient norm: 33.25: 33%|###3 | 208/625 [00:30<01:01, 6.79it/s]
reward: -3.8752, last reward: -4.2307, gradient norm: 10.76: 33%|###3 | 208/625 [00:30<01:01, 6.79it/s]
reward: -3.8752, last reward: -4.2307, gradient norm: 10.76: 33%|###3 | 209/625 [00:30<01:01, 6.78it/s]
reward: -3.5250, last reward: -1.4869, gradient norm: 40.8: 33%|###3 | 209/625 [00:30<01:01, 6.78it/s]
reward: -3.5250, last reward: -1.4869, gradient norm: 40.8: 34%|###3 | 210/625 [00:30<01:01, 6.76it/s]
reward: -3.7837, last reward: -2.5762, gradient norm: 193.3: 34%|###3 | 210/625 [00:30<01:01, 6.76it/s]
reward: -3.7837, last reward: -2.5762, gradient norm: 193.3: 34%|###3 | 211/625 [00:30<01:01, 6.74it/s]
reward: -3.6661, last reward: -1.8600, gradient norm: 136.5: 34%|###3 | 211/625 [00:30<01:01, 6.74it/s]
reward: -3.6661, last reward: -1.8600, gradient norm: 136.5: 34%|###3 | 212/625 [00:30<01:01, 6.73it/s]
reward: -4.2502, last reward: -3.1752, gradient norm: 21.44: 34%|###3 | 212/625 [00:31<01:01, 6.73it/s]
reward: -4.2502, last reward: -3.1752, gradient norm: 21.44: 34%|###4 | 213/625 [00:31<01:01, 6.74it/s]
reward: -4.3075, last reward: -2.8871, gradient norm: 30.65: 34%|###4 | 213/625 [00:31<01:01, 6.74it/s]
reward: -4.3075, last reward: -2.8871, gradient norm: 30.65: 34%|###4 | 214/625 [00:31<01:00, 6.75it/s]
reward: -3.9406, last reward: -2.8090, gradient norm: 20.18: 34%|###4 | 214/625 [00:31<01:00, 6.75it/s]
reward: -3.9406, last reward: -2.8090, gradient norm: 20.18: 34%|###4 | 215/625 [00:31<01:00, 6.75it/s]
reward: -3.6291, last reward: -2.8923, gradient norm: 7.876: 34%|###4 | 215/625 [00:31<01:00, 6.75it/s]
reward: -3.6291, last reward: -2.8923, gradient norm: 7.876: 35%|###4 | 216/625 [00:31<01:00, 6.75it/s]
reward: -3.5112, last reward: -3.9504, gradient norm: 3.21e+03: 35%|###4 | 216/625 [00:31<01:00, 6.75it/s]
reward: -3.5112, last reward: -3.9504, gradient norm: 3.21e+03: 35%|###4 | 217/625 [00:31<01:00, 6.74it/s]
reward: -3.7431, last reward: -2.7880, gradient norm: 13.73: 35%|###4 | 217/625 [00:31<01:00, 6.74it/s]
reward: -3.7431, last reward: -2.7880, gradient norm: 13.73: 35%|###4 | 218/625 [00:31<01:00, 6.75it/s]
reward: -3.4463, last reward: -4.5432, gradient norm: 32.37: 35%|###4 | 218/625 [00:31<01:00, 6.75it/s]
reward: -3.4463, last reward: -4.5432, gradient norm: 32.37: 35%|###5 | 219/625 [00:31<01:00, 6.74it/s]
reward: -3.3793, last reward: -3.3313, gradient norm: 60.63: 35%|###5 | 219/625 [00:32<01:00, 6.74it/s]
reward: -3.3793, last reward: -3.3313, gradient norm: 60.63: 35%|###5 | 220/625 [00:32<01:00, 6.74it/s]
reward: -3.8843, last reward: -3.0369, gradient norm: 5.065: 35%|###5 | 220/625 [00:32<01:00, 6.74it/s]
reward: -3.8843, last reward: -3.0369, gradient norm: 5.065: 35%|###5 | 221/625 [00:32<00:59, 6.75it/s]
reward: -3.4828, last reward: -3.8391, gradient norm: 59.85: 35%|###5 | 221/625 [00:32<00:59, 6.75it/s]
reward: -3.4828, last reward: -3.8391, gradient norm: 59.85: 36%|###5 | 222/625 [00:32<00:59, 6.74it/s]
reward: -3.6265, last reward: -4.2913, gradient norm: 8.947: 36%|###5 | 222/625 [00:32<00:59, 6.74it/s]
reward: -3.6265, last reward: -4.2913, gradient norm: 8.947: 36%|###5 | 223/625 [00:32<00:59, 6.75it/s]
reward: -3.5541, last reward: -4.1252, gradient norm: 255.9: 36%|###5 | 223/625 [00:32<00:59, 6.75it/s]
reward: -3.5541, last reward: -4.1252, gradient norm: 255.9: 36%|###5 | 224/625 [00:32<00:59, 6.78it/s]
reward: -3.7342, last reward: -2.2396, gradient norm: 7.995: 36%|###5 | 224/625 [00:32<00:59, 6.78it/s]
reward: -3.7342, last reward: -2.2396, gradient norm: 7.995: 36%|###6 | 225/625 [00:32<00:59, 6.78it/s]
reward: -3.5936, last reward: -4.1924, gradient norm: 59.49: 36%|###6 | 225/625 [00:32<00:59, 6.78it/s]
reward: -3.5936, last reward: -4.1924, gradient norm: 59.49: 36%|###6 | 226/625 [00:32<00:58, 6.77it/s]
reward: -3.9975, last reward: -4.2045, gradient norm: 21.77: 36%|###6 | 226/625 [00:33<00:58, 6.77it/s]
reward: -3.9975, last reward: -4.2045, gradient norm: 21.77: 36%|###6 | 227/625 [00:33<00:58, 6.76it/s]
reward: -3.8367, last reward: -1.9540, gradient norm: 32.26: 36%|###6 | 227/625 [00:33<00:58, 6.76it/s]
reward: -3.8367, last reward: -1.9540, gradient norm: 32.26: 36%|###6 | 228/625 [00:33<00:58, 6.76it/s]
reward: -3.7259, last reward: -3.6743, gradient norm: 28.62: 36%|###6 | 228/625 [00:33<00:58, 6.76it/s]
reward: -3.7259, last reward: -3.6743, gradient norm: 28.62: 37%|###6 | 229/625 [00:33<00:58, 6.75it/s]
reward: -3.4827, last reward: -3.7528, gradient norm: 64.85: 37%|###6 | 229/625 [00:33<00:58, 6.75it/s]
reward: -3.4827, last reward: -3.7528, gradient norm: 64.85: 37%|###6 | 230/625 [00:33<00:58, 6.75it/s]
reward: -3.7361, last reward: -3.8756, gradient norm: 24.69: 37%|###6 | 230/625 [00:33<00:58, 6.75it/s]
reward: -3.7361, last reward: -3.8756, gradient norm: 24.69: 37%|###6 | 231/625 [00:33<00:58, 6.74it/s]
reward: -3.7646, last reward: -3.1116, gradient norm: 14.25: 37%|###6 | 231/625 [00:33<00:58, 6.74it/s]
reward: -3.7646, last reward: -3.1116, gradient norm: 14.25: 37%|###7 | 232/625 [00:33<00:58, 6.74it/s]
reward: -3.5426, last reward: -2.8385, gradient norm: 34.07: 37%|###7 | 232/625 [00:34<00:58, 6.74it/s]
reward: -3.5426, last reward: -2.8385, gradient norm: 34.07: 37%|###7 | 233/625 [00:34<00:58, 6.74it/s]
reward: -3.5662, last reward: -1.8585, gradient norm: 11.26: 37%|###7 | 233/625 [00:34<00:58, 6.74it/s]
reward: -3.5662, last reward: -1.8585, gradient norm: 11.26: 37%|###7 | 234/625 [00:34<00:58, 6.74it/s]
reward: -3.8234, last reward: -2.7930, gradient norm: 32.18: 37%|###7 | 234/625 [00:34<00:58, 6.74it/s]
reward: -3.8234, last reward: -2.7930, gradient norm: 32.18: 38%|###7 | 235/625 [00:34<00:57, 6.75it/s]
reward: -4.2648, last reward: -4.9309, gradient norm: 24.83: 38%|###7 | 235/625 [00:34<00:57, 6.75it/s]
reward: -4.2648, last reward: -4.9309, gradient norm: 24.83: 38%|###7 | 236/625 [00:34<00:57, 6.75it/s]
reward: -4.2039, last reward: -3.6817, gradient norm: 19.24: 38%|###7 | 236/625 [00:34<00:57, 6.75it/s]
reward: -4.2039, last reward: -3.6817, gradient norm: 19.24: 38%|###7 | 237/625 [00:34<00:57, 6.75it/s]
reward: -4.0943, last reward: -3.1533, gradient norm: 145.1: 38%|###7 | 237/625 [00:34<00:57, 6.75it/s]
reward: -4.0943, last reward: -3.1533, gradient norm: 145.1: 38%|###8 | 238/625 [00:34<00:57, 6.77it/s]
reward: -4.3045, last reward: -3.0483, gradient norm: 20.89: 38%|###8 | 238/625 [00:34<00:57, 6.77it/s]
reward: -4.3045, last reward: -3.0483, gradient norm: 20.89: 38%|###8 | 239/625 [00:34<00:57, 6.76it/s]
reward: -4.4128, last reward: -5.2528, gradient norm: 24.97: 38%|###8 | 239/625 [00:35<00:57, 6.76it/s]
reward: -4.4128, last reward: -5.2528, gradient norm: 24.97: 38%|###8 | 240/625 [00:35<00:57, 6.75it/s]
reward: -4.6415, last reward: -8.0201, gradient norm: 26.74: 38%|###8 | 240/625 [00:35<00:57, 6.75it/s]
reward: -4.6415, last reward: -8.0201, gradient norm: 26.74: 39%|###8 | 241/625 [00:35<00:56, 6.75it/s]
reward: -4.4437, last reward: -5.4365, gradient norm: 132.7: 39%|###8 | 241/625 [00:35<00:56, 6.75it/s]
reward: -4.4437, last reward: -5.4365, gradient norm: 132.7: 39%|###8 | 242/625 [00:35<00:56, 6.74it/s]
reward: -4.0358, last reward: -3.4943, gradient norm: 11.46: 39%|###8 | 242/625 [00:35<00:56, 6.74it/s]
reward: -4.0358, last reward: -3.4943, gradient norm: 11.46: 39%|###8 | 243/625 [00:35<00:56, 6.75it/s]
reward: -4.1272, last reward: -3.5003, gradient norm: 68.09: 39%|###8 | 243/625 [00:35<00:56, 6.75it/s]
reward: -4.1272, last reward: -3.5003, gradient norm: 68.09: 39%|###9 | 244/625 [00:35<00:56, 6.74it/s]
reward: -4.1180, last reward: -4.2637, gradient norm: 39.25: 39%|###9 | 244/625 [00:35<00:56, 6.74it/s]
reward: -4.1180, last reward: -4.2637, gradient norm: 39.25: 39%|###9 | 245/625 [00:35<00:56, 6.74it/s]
reward: -4.7197, last reward: -3.0873, gradient norm: 12.2: 39%|###9 | 245/625 [00:35<00:56, 6.74it/s]
reward: -4.7197, last reward: -3.0873, gradient norm: 12.2: 39%|###9 | 246/625 [00:35<00:56, 6.73it/s]
reward: -4.2917, last reward: -3.6656, gradient norm: 17.17: 39%|###9 | 246/625 [00:36<00:56, 6.73it/s]
reward: -4.2917, last reward: -3.6656, gradient norm: 17.17: 40%|###9 | 247/625 [00:36<00:56, 6.73it/s]
reward: -4.0160, last reward: -3.0738, gradient norm: 43.07: 40%|###9 | 247/625 [00:36<00:56, 6.73it/s]
reward: -4.0160, last reward: -3.0738, gradient norm: 43.07: 40%|###9 | 248/625 [00:36<00:55, 6.76it/s]
reward: -4.3689, last reward: -4.0120, gradient norm: 11.81: 40%|###9 | 248/625 [00:36<00:55, 6.76it/s]
reward: -4.3689, last reward: -4.0120, gradient norm: 11.81: 40%|###9 | 249/625 [00:36<00:55, 6.78it/s]
reward: -4.5570, last reward: -7.0475, gradient norm: 22.45: 40%|###9 | 249/625 [00:36<00:55, 6.78it/s]
reward: -4.5570, last reward: -7.0475, gradient norm: 22.45: 40%|#### | 250/625 [00:36<00:55, 6.77it/s]
reward: -4.4423, last reward: -5.2220, gradient norm: 18.4: 40%|#### | 250/625 [00:36<00:55, 6.77it/s]
reward: -4.4423, last reward: -5.2220, gradient norm: 18.4: 40%|#### | 251/625 [00:36<00:55, 6.75it/s]
reward: -4.2118, last reward: -4.6803, gradient norm: 15.86: 40%|#### | 251/625 [00:36<00:55, 6.75it/s]
reward: -4.2118, last reward: -4.6803, gradient norm: 15.86: 40%|#### | 252/625 [00:36<00:55, 6.74it/s]
reward: -4.1465, last reward: -3.7214, gradient norm: 25.93: 40%|#### | 252/625 [00:36<00:55, 6.74it/s]
reward: -4.1465, last reward: -3.7214, gradient norm: 25.93: 40%|#### | 253/625 [00:36<00:55, 6.76it/s]
reward: -3.8801, last reward: -2.7034, gradient norm: 103.6: 40%|#### | 253/625 [00:37<00:55, 6.76it/s]
reward: -3.8801, last reward: -2.7034, gradient norm: 103.6: 41%|#### | 254/625 [00:37<00:54, 6.79it/s]
reward: -3.9136, last reward: -4.4076, gradient norm: 17.63: 41%|#### | 254/625 [00:37<00:54, 6.79it/s]
reward: -3.9136, last reward: -4.4076, gradient norm: 17.63: 41%|#### | 255/625 [00:37<00:54, 6.82it/s]
reward: -3.7589, last reward: -4.5013, gradient norm: 143.3: 41%|#### | 255/625 [00:37<00:54, 6.82it/s]
reward: -3.7589, last reward: -4.5013, gradient norm: 143.3: 41%|#### | 256/625 [00:37<00:54, 6.79it/s]
reward: -3.8150, last reward: -3.2241, gradient norm: 113.9: 41%|#### | 256/625 [00:37<00:54, 6.79it/s]
reward: -3.8150, last reward: -3.2241, gradient norm: 113.9: 41%|####1 | 257/625 [00:37<00:53, 6.82it/s]
reward: -4.0753, last reward: -3.8081, gradient norm: 14.8: 41%|####1 | 257/625 [00:37<00:53, 6.82it/s]
reward: -4.0753, last reward: -3.8081, gradient norm: 14.8: 41%|####1 | 258/625 [00:37<00:53, 6.82it/s]
reward: -4.1951, last reward: -4.8314, gradient norm: 27.63: 41%|####1 | 258/625 [00:37<00:53, 6.82it/s]
reward: -4.1951, last reward: -4.8314, gradient norm: 27.63: 41%|####1 | 259/625 [00:37<00:53, 6.83it/s]
reward: -4.0038, last reward: -2.5333, gradient norm: 42.85: 41%|####1 | 259/625 [00:37<00:53, 6.83it/s]
reward: -4.0038, last reward: -2.5333, gradient norm: 42.85: 42%|####1 | 260/625 [00:37<00:53, 6.85it/s]
reward: -4.0889, last reward: -2.4616, gradient norm: 13.78: 42%|####1 | 260/625 [00:38<00:53, 6.85it/s]
reward: -4.0889, last reward: -2.4616, gradient norm: 13.78: 42%|####1 | 261/625 [00:38<00:53, 6.86it/s]
reward: -4.0655, last reward: -2.6873, gradient norm: 10.98: 42%|####1 | 261/625 [00:38<00:53, 6.86it/s]
reward: -4.0655, last reward: -2.6873, gradient norm: 10.98: 42%|####1 | 262/625 [00:38<00:52, 6.92it/s]
reward: -3.8333, last reward: -1.9476, gradient norm: 13.47: 42%|####1 | 262/625 [00:38<00:52, 6.92it/s]
reward: -3.8333, last reward: -1.9476, gradient norm: 13.47: 42%|####2 | 263/625 [00:38<00:52, 6.93it/s]
reward: -3.7554, last reward: -4.3798, gradient norm: 41.76: 42%|####2 | 263/625 [00:38<00:52, 6.93it/s]
reward: -3.7554, last reward: -4.3798, gradient norm: 41.76: 42%|####2 | 264/625 [00:38<00:51, 6.97it/s]
reward: -3.3717, last reward: -2.3947, gradient norm: 6.529: 42%|####2 | 264/625 [00:38<00:51, 6.97it/s]
reward: -3.3717, last reward: -2.3947, gradient norm: 6.529: 42%|####2 | 265/625 [00:38<00:51, 6.99it/s]
reward: -4.3060, last reward: -4.6495, gradient norm: 11.24: 42%|####2 | 265/625 [00:38<00:51, 6.99it/s]
reward: -4.3060, last reward: -4.6495, gradient norm: 11.24: 43%|####2 | 266/625 [00:38<00:51, 7.01it/s]
reward: -4.7467, last reward: -5.8889, gradient norm: 12.35: 43%|####2 | 266/625 [00:38<00:51, 7.01it/s]
reward: -4.7467, last reward: -5.8889, gradient norm: 12.35: 43%|####2 | 267/625 [00:38<00:50, 7.03it/s]
reward: -4.9281, last reward: -4.8457, gradient norm: 6.591: 43%|####2 | 267/625 [00:39<00:50, 7.03it/s]
reward: -4.9281, last reward: -4.8457, gradient norm: 6.591: 43%|####2 | 268/625 [00:39<00:50, 7.03it/s]
reward: -4.7137, last reward: -4.0536, gradient norm: 5.771: 43%|####2 | 268/625 [00:39<00:50, 7.03it/s]
reward: -4.7137, last reward: -4.0536, gradient norm: 5.771: 43%|####3 | 269/625 [00:39<00:50, 6.99it/s]
reward: -4.7197, last reward: -4.1651, gradient norm: 5.388: 43%|####3 | 269/625 [00:39<00:50, 6.99it/s]
reward: -4.7197, last reward: -4.1651, gradient norm: 5.388: 43%|####3 | 270/625 [00:39<00:50, 6.99it/s]
reward: -4.8246, last reward: -5.5709, gradient norm: 8.281: 43%|####3 | 270/625 [00:39<00:50, 6.99it/s]
reward: -4.8246, last reward: -5.5709, gradient norm: 8.281: 43%|####3 | 271/625 [00:39<00:50, 7.01it/s]
reward: -4.7502, last reward: -5.0521, gradient norm: 9.032: 43%|####3 | 271/625 [00:39<00:50, 7.01it/s]
reward: -4.7502, last reward: -5.0521, gradient norm: 9.032: 44%|####3 | 272/625 [00:39<00:50, 7.03it/s]
reward: -4.5475, last reward: -4.7253, gradient norm: 21.18: 44%|####3 | 272/625 [00:39<00:50, 7.03it/s]
reward: -4.5475, last reward: -4.7253, gradient norm: 21.18: 44%|####3 | 273/625 [00:39<00:50, 7.02it/s]
reward: -4.2856, last reward: -3.7130, gradient norm: 13.53: 44%|####3 | 273/625 [00:39<00:50, 7.02it/s]
reward: -4.2856, last reward: -3.7130, gradient norm: 13.53: 44%|####3 | 274/625 [00:39<00:50, 6.99it/s]
reward: -3.2778, last reward: -3.4122, gradient norm: 28.52: 44%|####3 | 274/625 [00:40<00:50, 6.99it/s]
reward: -3.2778, last reward: -3.4122, gradient norm: 28.52: 44%|####4 | 275/625 [00:40<00:49, 7.00it/s]
reward: -3.8368, last reward: -2.1841, gradient norm: 2.07: 44%|####4 | 275/625 [00:40<00:49, 7.00it/s]
reward: -3.8368, last reward: -2.1841, gradient norm: 2.07: 44%|####4 | 276/625 [00:40<00:49, 7.02it/s]
reward: -3.9622, last reward: -3.1603, gradient norm: 1.003e+03: 44%|####4 | 276/625 [00:40<00:49, 7.02it/s]
reward: -3.9622, last reward: -3.1603, gradient norm: 1.003e+03: 44%|####4 | 277/625 [00:40<00:49, 7.02it/s]
reward: -4.0247, last reward: -2.9830, gradient norm: 8.346: 44%|####4 | 277/625 [00:40<00:49, 7.02it/s]
reward: -4.0247, last reward: -2.9830, gradient norm: 8.346: 44%|####4 | 278/625 [00:40<00:49, 7.03it/s]
reward: -4.2238, last reward: -4.6418, gradient norm: 14.55: 44%|####4 | 278/625 [00:40<00:49, 7.03it/s]
reward: -4.2238, last reward: -4.6418, gradient norm: 14.55: 45%|####4 | 279/625 [00:40<00:49, 7.04it/s]
reward: -4.0626, last reward: -4.2538, gradient norm: 17.88: 45%|####4 | 279/625 [00:40<00:49, 7.04it/s]
reward: -4.0626, last reward: -4.2538, gradient norm: 17.88: 45%|####4 | 280/625 [00:40<00:49, 7.03it/s]
reward: -4.0149, last reward: -3.7380, gradient norm: 13.13: 45%|####4 | 280/625 [00:40<00:49, 7.03it/s]
reward: -4.0149, last reward: -3.7380, gradient norm: 13.13: 45%|####4 | 281/625 [00:40<00:49, 6.98it/s]
reward: -4.2167, last reward: -2.8911, gradient norm: 11.41: 45%|####4 | 281/625 [00:41<00:49, 6.98it/s]
reward: -4.2167, last reward: -2.8911, gradient norm: 11.41: 45%|####5 | 282/625 [00:41<00:49, 7.00it/s]
reward: -3.8725, last reward: -4.1983, gradient norm: 18.88: 45%|####5 | 282/625 [00:41<00:49, 7.00it/s]
reward: -3.8725, last reward: -4.1983, gradient norm: 18.88: 45%|####5 | 283/625 [00:41<00:48, 7.02it/s]
reward: -2.8142, last reward: -2.3709, gradient norm: 43.73: 45%|####5 | 283/625 [00:41<00:48, 7.02it/s]
reward: -2.8142, last reward: -2.3709, gradient norm: 43.73: 45%|####5 | 284/625 [00:41<00:48, 7.03it/s]
reward: -3.2022, last reward: -2.4989, gradient norm: 11.14: 45%|####5 | 284/625 [00:41<00:48, 7.03it/s]
reward: -3.2022, last reward: -2.4989, gradient norm: 11.14: 46%|####5 | 285/625 [00:41<00:48, 7.03it/s]
reward: -3.6464, last reward: -1.6210, gradient norm: 43.37: 46%|####5 | 285/625 [00:41<00:48, 7.03it/s]
reward: -3.6464, last reward: -1.6210, gradient norm: 43.37: 46%|####5 | 286/625 [00:41<00:48, 6.99it/s]
reward: -3.9726, last reward: -3.0820, gradient norm: 39.93: 46%|####5 | 286/625 [00:41<00:48, 6.99it/s]
reward: -3.9726, last reward: -3.0820, gradient norm: 39.93: 46%|####5 | 287/625 [00:41<00:48, 7.00it/s]
reward: -3.6975, last reward: -2.9091, gradient norm: 29.46: 46%|####5 | 287/625 [00:41<00:48, 7.00it/s]
reward: -3.6975, last reward: -2.9091, gradient norm: 29.46: 46%|####6 | 288/625 [00:41<00:48, 6.97it/s]
reward: -3.4926, last reward: -2.4791, gradient norm: 160.7: 46%|####6 | 288/625 [00:42<00:48, 6.97it/s]
reward: -3.4926, last reward: -2.4791, gradient norm: 160.7: 46%|####6 | 289/625 [00:42<00:48, 7.00it/s]
reward: -3.0905, last reward: -1.3500, gradient norm: 31.38: 46%|####6 | 289/625 [00:42<00:48, 7.00it/s]
reward: -3.0905, last reward: -1.3500, gradient norm: 31.38: 46%|####6 | 290/625 [00:42<00:47, 7.02it/s]
reward: -3.2287, last reward: -2.7137, gradient norm: 26.31: 46%|####6 | 290/625 [00:42<00:47, 7.02it/s]
reward: -3.2287, last reward: -2.7137, gradient norm: 26.31: 47%|####6 | 291/625 [00:42<00:47, 7.03it/s]
reward: -2.9918, last reward: -1.5543, gradient norm: 29.73: 47%|####6 | 291/625 [00:42<00:47, 7.03it/s]
reward: -2.9918, last reward: -1.5543, gradient norm: 29.73: 47%|####6 | 292/625 [00:42<00:47, 7.03it/s]
reward: -2.9245, last reward: -0.6444, gradient norm: 2.631: 47%|####6 | 292/625 [00:42<00:47, 7.03it/s]
reward: -2.9245, last reward: -0.6444, gradient norm: 2.631: 47%|####6 | 293/625 [00:42<00:47, 7.04it/s]
reward: -3.0448, last reward: -0.4769, gradient norm: 7.266: 47%|####6 | 293/625 [00:42<00:47, 7.04it/s]
reward: -3.0448, last reward: -0.4769, gradient norm: 7.266: 47%|####7 | 294/625 [00:42<00:47, 7.04it/s]
reward: -2.8566, last reward: -1.7208, gradient norm: 25.22: 47%|####7 | 294/625 [00:42<00:47, 7.04it/s]
reward: -2.8566, last reward: -1.7208, gradient norm: 25.22: 47%|####7 | 295/625 [00:42<00:47, 7.00it/s]
reward: -2.8872, last reward: -1.0966, gradient norm: 8.247: 47%|####7 | 295/625 [00:43<00:47, 7.00it/s]
reward: -2.8872, last reward: -1.0966, gradient norm: 8.247: 47%|####7 | 296/625 [00:43<00:46, 7.02it/s]
reward: -2.5303, last reward: -0.1537, gradient norm: 2.023: 47%|####7 | 296/625 [00:43<00:46, 7.02it/s]
reward: -2.5303, last reward: -0.1537, gradient norm: 2.023: 48%|####7 | 297/625 [00:43<00:46, 7.02it/s]
reward: -2.6817, last reward: -0.2682, gradient norm: 7.564: 48%|####7 | 297/625 [00:43<00:46, 7.02it/s]
reward: -2.6817, last reward: -0.2682, gradient norm: 7.564: 48%|####7 | 298/625 [00:43<00:46, 7.03it/s]
reward: -2.4318, last reward: -0.5063, gradient norm: 14.87: 48%|####7 | 298/625 [00:43<00:46, 7.03it/s]
reward: -2.4318, last reward: -0.5063, gradient norm: 14.87: 48%|####7 | 299/625 [00:43<00:46, 6.98it/s]
reward: -2.7475, last reward: -1.4190, gradient norm: 21.66: 48%|####7 | 299/625 [00:43<00:46, 6.98it/s]
reward: -2.7475, last reward: -1.4190, gradient norm: 21.66: 48%|####8 | 300/625 [00:43<00:46, 6.95it/s]
reward: -2.8186, last reward: -2.5077, gradient norm: 22.4: 48%|####8 | 300/625 [00:43<00:46, 6.95it/s]
reward: -2.8186, last reward: -2.5077, gradient norm: 22.4: 48%|####8 | 301/625 [00:43<00:46, 6.97it/s]
reward: -3.1883, last reward: -1.5291, gradient norm: 7.472: 48%|####8 | 301/625 [00:43<00:46, 6.97it/s]
reward: -3.1883, last reward: -1.5291, gradient norm: 7.472: 48%|####8 | 302/625 [00:43<00:46, 6.95it/s]
reward: -2.1256, last reward: -0.3998, gradient norm: 11.01: 48%|####8 | 302/625 [00:44<00:46, 6.95it/s]
reward: -2.1256, last reward: -0.3998, gradient norm: 11.01: 48%|####8 | 303/625 [00:44<00:46, 6.98it/s]
reward: -2.3622, last reward: -0.0930, gradient norm: 1.626: 48%|####8 | 303/625 [00:44<00:46, 6.98it/s]
reward: -2.3622, last reward: -0.0930, gradient norm: 1.626: 49%|####8 | 304/625 [00:44<00:45, 7.01it/s]
reward: -1.9500, last reward: -0.0075, gradient norm: 0.5664: 49%|####8 | 304/625 [00:44<00:45, 7.01it/s]
reward: -1.9500, last reward: -0.0075, gradient norm: 0.5664: 49%|####8 | 305/625 [00:44<00:45, 7.02it/s]
reward: -2.5697, last reward: -0.3024, gradient norm: 22.61: 49%|####8 | 305/625 [00:44<00:45, 7.02it/s]
reward: -2.5697, last reward: -0.3024, gradient norm: 22.61: 49%|####8 | 306/625 [00:44<00:45, 7.02it/s]
reward: -2.3117, last reward: -0.0052, gradient norm: 1.006: 49%|####8 | 306/625 [00:44<00:45, 7.02it/s]
reward: -2.3117, last reward: -0.0052, gradient norm: 1.006: 49%|####9 | 307/625 [00:44<00:45, 7.03it/s]
reward: -2.0981, last reward: -0.0018, gradient norm: 0.9312: 49%|####9 | 307/625 [00:44<00:45, 7.03it/s]
reward: -2.0981, last reward: -0.0018, gradient norm: 0.9312: 49%|####9 | 308/625 [00:44<00:45, 7.04it/s]
reward: -2.5140, last reward: -0.3873, gradient norm: 3.93: 49%|####9 | 308/625 [00:44<00:45, 7.04it/s]
reward: -2.5140, last reward: -0.3873, gradient norm: 3.93: 49%|####9 | 309/625 [00:44<00:44, 7.05it/s]
reward: -2.0411, last reward: -0.2650, gradient norm: 3.183: 49%|####9 | 309/625 [00:45<00:44, 7.05it/s]
reward: -2.0411, last reward: -0.2650, gradient norm: 3.183: 50%|####9 | 310/625 [00:45<00:44, 7.05it/s]
reward: -2.1656, last reward: -0.0228, gradient norm: 2.004: 50%|####9 | 310/625 [00:45<00:44, 7.05it/s]
reward: -2.1656, last reward: -0.0228, gradient norm: 2.004: 50%|####9 | 311/625 [00:45<00:44, 7.06it/s]
reward: -2.1196, last reward: -0.2478, gradient norm: 11.78: 50%|####9 | 311/625 [00:45<00:44, 7.06it/s]
reward: -2.1196, last reward: -0.2478, gradient norm: 11.78: 50%|####9 | 312/625 [00:45<00:44, 7.06it/s]
reward: -2.7353, last reward: -3.0812, gradient norm: 82.91: 50%|####9 | 312/625 [00:45<00:44, 7.06it/s]
reward: -2.7353, last reward: -3.0812, gradient norm: 82.91: 50%|##### | 313/625 [00:45<00:44, 7.07it/s]
reward: -3.0995, last reward: -2.3022, gradient norm: 8.758: 50%|##### | 313/625 [00:45<00:44, 7.07it/s]
reward: -3.0995, last reward: -2.3022, gradient norm: 8.758: 50%|##### | 314/625 [00:45<00:44, 7.06it/s]
reward: -3.1406, last reward: -2.4626, gradient norm: 15.99: 50%|##### | 314/625 [00:45<00:44, 7.06it/s]
reward: -3.1406, last reward: -2.4626, gradient norm: 15.99: 50%|##### | 315/625 [00:45<00:43, 7.06it/s]
reward: -3.2156, last reward: -1.9055, gradient norm: 7.851: 50%|##### | 315/625 [00:45<00:43, 7.06it/s]
reward: -3.2156, last reward: -1.9055, gradient norm: 7.851: 51%|##### | 316/625 [00:45<00:43, 7.07it/s]
reward: -3.1953, last reward: -2.3774, gradient norm: 19.78: 51%|##### | 316/625 [00:46<00:43, 7.07it/s]
reward: -3.1953, last reward: -2.3774, gradient norm: 19.78: 51%|##### | 317/625 [00:46<00:43, 7.07it/s]
reward: -2.6385, last reward: -0.9917, gradient norm: 16.15: 51%|##### | 317/625 [00:46<00:43, 7.07it/s]
reward: -2.6385, last reward: -0.9917, gradient norm: 16.15: 51%|##### | 318/625 [00:46<00:43, 7.06it/s]
reward: -2.2764, last reward: -0.0536, gradient norm: 2.905: 51%|##### | 318/625 [00:46<00:43, 7.06it/s]
reward: -2.2764, last reward: -0.0536, gradient norm: 2.905: 51%|#####1 | 319/625 [00:46<00:43, 7.07it/s]
reward: -2.6391, last reward: -1.9317, gradient norm: 23.78: 51%|#####1 | 319/625 [00:46<00:43, 7.07it/s]
reward: -2.6391, last reward: -1.9317, gradient norm: 23.78: 51%|#####1 | 320/625 [00:46<00:43, 7.06it/s]
reward: -2.9748, last reward: -4.2679, gradient norm: 59.43: 51%|#####1 | 320/625 [00:46<00:43, 7.06it/s]
reward: -2.9748, last reward: -4.2679, gradient norm: 59.43: 51%|#####1 | 321/625 [00:46<00:43, 7.06it/s]
reward: -2.8495, last reward: -4.5125, gradient norm: 52.19: 51%|#####1 | 321/625 [00:46<00:43, 7.06it/s]
reward: -2.8495, last reward: -4.5125, gradient norm: 52.19: 52%|#####1 | 322/625 [00:46<00:42, 7.06it/s]
reward: -2.8177, last reward: -2.6602, gradient norm: 52.75: 52%|#####1 | 322/625 [00:46<00:42, 7.06it/s]
reward: -2.8177, last reward: -2.6602, gradient norm: 52.75: 52%|#####1 | 323/625 [00:46<00:43, 7.00it/s]
reward: -2.0704, last reward: -0.5776, gradient norm: 59.07: 52%|#####1 | 323/625 [00:47<00:43, 7.00it/s]
reward: -2.0704, last reward: -0.5776, gradient norm: 59.07: 52%|#####1 | 324/625 [00:47<00:42, 7.02it/s]
reward: -1.9833, last reward: -0.1339, gradient norm: 4.402: 52%|#####1 | 324/625 [00:47<00:42, 7.02it/s]
reward: -1.9833, last reward: -0.1339, gradient norm: 4.402: 52%|#####2 | 325/625 [00:47<00:42, 7.04it/s]
reward: -2.2760, last reward: -2.1238, gradient norm: 30.36: 52%|#####2 | 325/625 [00:47<00:42, 7.04it/s]
reward: -2.2760, last reward: -2.1238, gradient norm: 30.36: 52%|#####2 | 326/625 [00:47<00:42, 7.04it/s]
reward: -2.9299, last reward: -5.0227, gradient norm: 100.5: 52%|#####2 | 326/625 [00:47<00:42, 7.04it/s]
reward: -2.9299, last reward: -5.0227, gradient norm: 100.5: 52%|#####2 | 327/625 [00:47<00:42, 7.05it/s]
reward: -2.7727, last reward: -2.1607, gradient norm: 336.7: 52%|#####2 | 327/625 [00:47<00:42, 7.05it/s]
reward: -2.7727, last reward: -2.1607, gradient norm: 336.7: 52%|#####2 | 328/625 [00:47<00:42, 7.05it/s]
reward: -2.3958, last reward: -0.3223, gradient norm: 2.763: 52%|#####2 | 328/625 [00:47<00:42, 7.05it/s]
reward: -2.3958, last reward: -0.3223, gradient norm: 2.763: 53%|#####2 | 329/625 [00:47<00:41, 7.05it/s]
reward: -2.4742, last reward: -0.1797, gradient norm: 47.32: 53%|#####2 | 329/625 [00:47<00:41, 7.05it/s]
reward: -2.4742, last reward: -0.1797, gradient norm: 47.32: 53%|#####2 | 330/625 [00:47<00:41, 7.04it/s]
reward: -2.0144, last reward: -0.0085, gradient norm: 4.791: 53%|#####2 | 330/625 [00:48<00:41, 7.04it/s]
reward: -2.0144, last reward: -0.0085, gradient norm: 4.791: 53%|#####2 | 331/625 [00:48<00:41, 7.05it/s]
reward: -1.8284, last reward: -0.0428, gradient norm: 12.29: 53%|#####2 | 331/625 [00:48<00:41, 7.05it/s]
reward: -1.8284, last reward: -0.0428, gradient norm: 12.29: 53%|#####3 | 332/625 [00:48<00:41, 7.05it/s]
reward: -2.5229, last reward: -0.0098, gradient norm: 0.7365: 53%|#####3 | 332/625 [00:48<00:41, 7.05it/s]
reward: -2.5229, last reward: -0.0098, gradient norm: 0.7365: 53%|#####3 | 333/625 [00:48<00:41, 7.05it/s]
reward: -2.4566, last reward: -0.0781, gradient norm: 2.086: 53%|#####3 | 333/625 [00:48<00:41, 7.05it/s]
reward: -2.4566, last reward: -0.0781, gradient norm: 2.086: 53%|#####3 | 334/625 [00:48<00:41, 7.06it/s]
reward: -2.3355, last reward: -0.0230, gradient norm: 1.311: 53%|#####3 | 334/625 [00:48<00:41, 7.06it/s]
reward: -2.3355, last reward: -0.0230, gradient norm: 1.311: 54%|#####3 | 335/625 [00:48<00:41, 7.03it/s]
reward: -1.9346, last reward: -0.0423, gradient norm: 1.076: 54%|#####3 | 335/625 [00:48<00:41, 7.03it/s]
reward: -1.9346, last reward: -0.0423, gradient norm: 1.076: 54%|#####3 | 336/625 [00:48<00:41, 7.04it/s]
reward: -2.3711, last reward: -0.1335, gradient norm: 0.6855: 54%|#####3 | 336/625 [00:48<00:41, 7.04it/s]
reward: -2.3711, last reward: -0.1335, gradient norm: 0.6855: 54%|#####3 | 337/625 [00:48<00:40, 7.05it/s]
reward: -2.0304, last reward: -0.0023, gradient norm: 0.8459: 54%|#####3 | 337/625 [00:49<00:40, 7.05it/s]
reward: -2.0304, last reward: -0.0023, gradient norm: 0.8459: 54%|#####4 | 338/625 [00:49<00:40, 7.05it/s]
reward: -1.9998, last reward: -0.4399, gradient norm: 13.1: 54%|#####4 | 338/625 [00:49<00:40, 7.05it/s]
reward: -1.9998, last reward: -0.4399, gradient norm: 13.1: 54%|#####4 | 339/625 [00:49<00:40, 7.05it/s]
reward: -2.2303, last reward: -2.1346, gradient norm: 45.99: 54%|#####4 | 339/625 [00:49<00:40, 7.05it/s]
reward: -2.2303, last reward: -2.1346, gradient norm: 45.99: 54%|#####4 | 340/625 [00:49<00:40, 7.05it/s]
reward: -2.2915, last reward: -1.7116, gradient norm: 40.34: 54%|#####4 | 340/625 [00:49<00:40, 7.05it/s]
reward: -2.2915, last reward: -1.7116, gradient norm: 40.34: 55%|#####4 | 341/625 [00:49<00:40, 7.06it/s]
reward: -2.5560, last reward: -0.0487, gradient norm: 1.195: 55%|#####4 | 341/625 [00:49<00:40, 7.06it/s]
reward: -2.5560, last reward: -0.0487, gradient norm: 1.195: 55%|#####4 | 342/625 [00:49<00:40, 7.06it/s]
reward: -2.5119, last reward: -0.0358, gradient norm: 1.061: 55%|#####4 | 342/625 [00:49<00:40, 7.06it/s]
reward: -2.5119, last reward: -0.0358, gradient norm: 1.061: 55%|#####4 | 343/625 [00:49<00:39, 7.06it/s]
reward: -2.3305, last reward: -0.3705, gradient norm: 1.957: 55%|#####4 | 343/625 [00:49<00:39, 7.06it/s]
reward: -2.3305, last reward: -0.3705, gradient norm: 1.957: 55%|#####5 | 344/625 [00:49<00:40, 6.99it/s]
reward: -2.6068, last reward: -0.2112, gradient norm: 13.83: 55%|#####5 | 344/625 [00:50<00:40, 6.99it/s]
reward: -2.6068, last reward: -0.2112, gradient norm: 13.83: 55%|#####5 | 345/625 [00:50<00:39, 7.01it/s]
reward: -2.5731, last reward: -1.8455, gradient norm: 66.75: 55%|#####5 | 345/625 [00:50<00:39, 7.01it/s]
reward: -2.5731, last reward: -1.8455, gradient norm: 66.75: 55%|#####5 | 346/625 [00:50<00:39, 6.98it/s]
reward: -2.3897, last reward: -0.0376, gradient norm: 1.608: 55%|#####5 | 346/625 [00:50<00:39, 6.98it/s]
reward: -2.3897, last reward: -0.0376, gradient norm: 1.608: 56%|#####5 | 347/625 [00:50<00:40, 6.91it/s]
reward: -2.2264, last reward: -0.0434, gradient norm: 2.012: 56%|#####5 | 347/625 [00:50<00:40, 6.91it/s]
reward: -2.2264, last reward: -0.0434, gradient norm: 2.012: 56%|#####5 | 348/625 [00:50<00:40, 6.88it/s]
reward: -2.1300, last reward: -0.1215, gradient norm: 2.557: 56%|#####5 | 348/625 [00:50<00:40, 6.88it/s]
reward: -2.1300, last reward: -0.1215, gradient norm: 2.557: 56%|#####5 | 349/625 [00:50<00:40, 6.85it/s]
reward: -2.0968, last reward: -0.0885, gradient norm: 3.389: 56%|#####5 | 349/625 [00:50<00:40, 6.85it/s]
reward: -2.0968, last reward: -0.0885, gradient norm: 3.389: 56%|#####6 | 350/625 [00:50<00:40, 6.84it/s]
reward: -2.1348, last reward: -0.0073, gradient norm: 0.5052: 56%|#####6 | 350/625 [00:50<00:40, 6.84it/s]
reward: -2.1348, last reward: -0.0073, gradient norm: 0.5052: 56%|#####6 | 351/625 [00:50<00:40, 6.83it/s]
reward: -2.4184, last reward: -3.2817, gradient norm: 108.6: 56%|#####6 | 351/625 [00:51<00:40, 6.83it/s]
reward: -2.4184, last reward: -3.2817, gradient norm: 108.6: 56%|#####6 | 352/625 [00:51<00:39, 6.83it/s]
reward: -2.3774, last reward: -1.8887, gradient norm: 54.07: 56%|#####6 | 352/625 [00:51<00:39, 6.83it/s]
reward: -2.3774, last reward: -1.8887, gradient norm: 54.07: 56%|#####6 | 353/625 [00:51<00:39, 6.82it/s]
reward: -2.4779, last reward: -0.1009, gradient norm: 10.91: 56%|#####6 | 353/625 [00:51<00:39, 6.82it/s]
reward: -2.4779, last reward: -0.1009, gradient norm: 10.91: 57%|#####6 | 354/625 [00:51<00:39, 6.83it/s]
reward: -2.2588, last reward: -0.0604, gradient norm: 2.599: 57%|#####6 | 354/625 [00:51<00:39, 6.83it/s]
reward: -2.2588, last reward: -0.0604, gradient norm: 2.599: 57%|#####6 | 355/625 [00:51<00:39, 6.90it/s]
reward: -2.4486, last reward: -0.1176, gradient norm: 3.656: 57%|#####6 | 355/625 [00:51<00:39, 6.90it/s]
reward: -2.4486, last reward: -0.1176, gradient norm: 3.656: 57%|#####6 | 356/625 [00:51<00:39, 6.86it/s]
reward: -2.2436, last reward: -0.0668, gradient norm: 2.724: 57%|#####6 | 356/625 [00:51<00:39, 6.86it/s]
reward: -2.2436, last reward: -0.0668, gradient norm: 2.724: 57%|#####7 | 357/625 [00:51<00:39, 6.84it/s]
reward: -1.8849, last reward: -0.0012, gradient norm: 5.326: 57%|#####7 | 357/625 [00:51<00:39, 6.84it/s]
reward: -1.8849, last reward: -0.0012, gradient norm: 5.326: 57%|#####7 | 358/625 [00:51<00:39, 6.82it/s]
reward: -2.7511, last reward: -0.8804, gradient norm: 13.6: 57%|#####7 | 358/625 [00:52<00:39, 6.82it/s]
reward: -2.7511, last reward: -0.8804, gradient norm: 13.6: 57%|#####7 | 359/625 [00:52<00:39, 6.82it/s]
reward: -2.8870, last reward: -3.6728, gradient norm: 33.56: 57%|#####7 | 359/625 [00:52<00:39, 6.82it/s]
reward: -2.8870, last reward: -3.6728, gradient norm: 33.56: 58%|#####7 | 360/625 [00:52<00:38, 6.83it/s]
reward: -2.8841, last reward: -2.5508, gradient norm: 30.93: 58%|#####7 | 360/625 [00:52<00:38, 6.83it/s]
reward: -2.8841, last reward: -2.5508, gradient norm: 30.93: 58%|#####7 | 361/625 [00:52<00:38, 6.85it/s]
reward: -2.5242, last reward: -1.0268, gradient norm: 33.15: 58%|#####7 | 361/625 [00:52<00:38, 6.85it/s]
reward: -2.5242, last reward: -1.0268, gradient norm: 33.15: 58%|#####7 | 362/625 [00:52<00:38, 6.86it/s]
reward: -2.3232, last reward: -0.0013, gradient norm: 0.6185: 58%|#####7 | 362/625 [00:52<00:38, 6.86it/s]
reward: -2.3232, last reward: -0.0013, gradient norm: 0.6185: 58%|#####8 | 363/625 [00:52<00:37, 6.91it/s]
reward: -2.1378, last reward: -0.0204, gradient norm: 1.337: 58%|#####8 | 363/625 [00:52<00:37, 6.91it/s]
reward: -2.1378, last reward: -0.0204, gradient norm: 1.337: 58%|#####8 | 364/625 [00:52<00:37, 6.94it/s]
reward: -2.2677, last reward: -0.0355, gradient norm: 1.685: 58%|#####8 | 364/625 [00:53<00:37, 6.94it/s]
reward: -2.2677, last reward: -0.0355, gradient norm: 1.685: 58%|#####8 | 365/625 [00:53<00:37, 6.90it/s]
reward: -2.4884, last reward: -0.0231, gradient norm: 1.213: 58%|#####8 | 365/625 [00:53<00:37, 6.90it/s]
reward: -2.4884, last reward: -0.0231, gradient norm: 1.213: 59%|#####8 | 366/625 [00:53<00:37, 6.86it/s]
reward: -2.0770, last reward: -0.0014, gradient norm: 0.6793: 59%|#####8 | 366/625 [00:53<00:37, 6.86it/s]
reward: -2.0770, last reward: -0.0014, gradient norm: 0.6793: 59%|#####8 | 367/625 [00:53<00:37, 6.84it/s]
reward: -1.9834, last reward: -0.0349, gradient norm: 1.863: 59%|#####8 | 367/625 [00:53<00:37, 6.84it/s]
reward: -1.9834, last reward: -0.0349, gradient norm: 1.863: 59%|#####8 | 368/625 [00:53<00:37, 6.82it/s]
reward: -2.6709, last reward: -0.1416, gradient norm: 5.462: 59%|#####8 | 368/625 [00:53<00:37, 6.82it/s]
reward: -2.6709, last reward: -0.1416, gradient norm: 5.462: 59%|#####9 | 369/625 [00:53<00:37, 6.82it/s]
reward: -2.5199, last reward: -3.9790, gradient norm: 47.67: 59%|#####9 | 369/625 [00:53<00:37, 6.82it/s]
reward: -2.5199, last reward: -3.9790, gradient norm: 47.67: 59%|#####9 | 370/625 [00:53<00:37, 6.82it/s]
reward: -2.9401, last reward: -3.7802, gradient norm: 32.47: 59%|#####9 | 370/625 [00:53<00:37, 6.82it/s]
reward: -2.9401, last reward: -3.7802, gradient norm: 32.47: 59%|#####9 | 371/625 [00:53<00:37, 6.80it/s]
reward: -2.6723, last reward: -3.6507, gradient norm: 45.1: 59%|#####9 | 371/625 [00:54<00:37, 6.80it/s]
reward: -2.6723, last reward: -3.6507, gradient norm: 45.1: 60%|#####9 | 372/625 [00:54<00:37, 6.81it/s]
reward: -2.2678, last reward: -0.6201, gradient norm: 32.94: 60%|#####9 | 372/625 [00:54<00:37, 6.81it/s]
reward: -2.2678, last reward: -0.6201, gradient norm: 32.94: 60%|#####9 | 373/625 [00:54<00:37, 6.81it/s]
reward: -2.2184, last reward: -0.0075, gradient norm: 0.7385: 60%|#####9 | 373/625 [00:54<00:37, 6.81it/s]
reward: -2.2184, last reward: -0.0075, gradient norm: 0.7385: 60%|#####9 | 374/625 [00:54<00:36, 6.80it/s]
reward: -2.6344, last reward: -0.0576, gradient norm: 1.617: 60%|#####9 | 374/625 [00:54<00:36, 6.80it/s]
reward: -2.6344, last reward: -0.0576, gradient norm: 1.617: 60%|###### | 375/625 [00:54<00:36, 6.80it/s]
reward: -1.9945, last reward: -0.0772, gradient norm: 2.567: 60%|###### | 375/625 [00:54<00:36, 6.80it/s]
reward: -1.9945, last reward: -0.0772, gradient norm: 2.567: 60%|###### | 376/625 [00:54<00:36, 6.80it/s]
reward: -1.7576, last reward: -0.0398, gradient norm: 1.961: 60%|###### | 376/625 [00:54<00:36, 6.80it/s]
reward: -1.7576, last reward: -0.0398, gradient norm: 1.961: 60%|###### | 377/625 [00:54<00:36, 6.80it/s]
reward: -2.3396, last reward: -0.0022, gradient norm: 1.094: 60%|###### | 377/625 [00:54<00:36, 6.80it/s]
reward: -2.3396, last reward: -0.0022, gradient norm: 1.094: 60%|###### | 378/625 [00:54<00:36, 6.79it/s]
reward: -2.3073, last reward: -0.4018, gradient norm: 29.23: 60%|###### | 378/625 [00:55<00:36, 6.79it/s]
reward: -2.3073, last reward: -0.4018, gradient norm: 29.23: 61%|###### | 379/625 [00:55<00:36, 6.79it/s]
reward: -2.3313, last reward: -1.1869, gradient norm: 38.62: 61%|###### | 379/625 [00:55<00:36, 6.79it/s]
reward: -2.3313, last reward: -1.1869, gradient norm: 38.62: 61%|###### | 380/625 [00:55<00:36, 6.80it/s]
reward: -2.0481, last reward: -0.1117, gradient norm: 5.321: 61%|###### | 380/625 [00:55<00:36, 6.80it/s]
reward: -2.0481, last reward: -0.1117, gradient norm: 5.321: 61%|###### | 381/625 [00:55<00:35, 6.80it/s]
reward: -1.6823, last reward: -0.0001, gradient norm: 1.981: 61%|###### | 381/625 [00:55<00:35, 6.80it/s]
reward: -1.6823, last reward: -0.0001, gradient norm: 1.981: 61%|######1 | 382/625 [00:55<00:35, 6.81it/s]
reward: -1.8305, last reward: -0.0210, gradient norm: 1.228: 61%|######1 | 382/625 [00:55<00:35, 6.81it/s]
reward: -1.8305, last reward: -0.0210, gradient norm: 1.228: 61%|######1 | 383/625 [00:55<00:35, 6.81it/s]
reward: -1.4908, last reward: -0.0272, gradient norm: 1.538: 61%|######1 | 383/625 [00:55<00:35, 6.81it/s]
reward: -1.4908, last reward: -0.0272, gradient norm: 1.538: 61%|######1 | 384/625 [00:55<00:35, 6.81it/s]
reward: -2.3267, last reward: -0.0111, gradient norm: 0.7965: 61%|######1 | 384/625 [00:55<00:35, 6.81it/s]
reward: -2.3267, last reward: -0.0111, gradient norm: 0.7965: 62%|######1 | 385/625 [00:55<00:35, 6.80it/s]
reward: -2.1796, last reward: -0.0039, gradient norm: 0.5396: 62%|######1 | 385/625 [00:56<00:35, 6.80it/s]
reward: -2.1796, last reward: -0.0039, gradient norm: 0.5396: 62%|######1 | 386/625 [00:56<00:35, 6.80it/s]
reward: -2.3757, last reward: -0.0490, gradient norm: 2.237: 62%|######1 | 386/625 [00:56<00:35, 6.80it/s]
reward: -2.3757, last reward: -0.0490, gradient norm: 2.237: 62%|######1 | 387/625 [00:56<00:34, 6.82it/s]
reward: -2.1394, last reward: -0.4187, gradient norm: 52.11: 62%|######1 | 387/625 [00:56<00:34, 6.82it/s]
reward: -2.1394, last reward: -0.4187, gradient norm: 52.11: 62%|######2 | 388/625 [00:56<00:34, 6.84it/s]
reward: -2.2986, last reward: -0.0038, gradient norm: 0.7954: 62%|######2 | 388/625 [00:56<00:34, 6.84it/s]
reward: -2.2986, last reward: -0.0038, gradient norm: 0.7954: 62%|######2 | 389/625 [00:56<00:34, 6.84it/s]
reward: -2.1274, last reward: -0.0063, gradient norm: 0.813: 62%|######2 | 389/625 [00:56<00:34, 6.84it/s]
reward: -2.1274, last reward: -0.0063, gradient norm: 0.813: 62%|######2 | 390/625 [00:56<00:34, 6.84it/s]
reward: -1.8706, last reward: -0.0114, gradient norm: 3.325: 62%|######2 | 390/625 [00:56<00:34, 6.84it/s]
reward: -1.8706, last reward: -0.0114, gradient norm: 3.325: 63%|######2 | 391/625 [00:56<00:34, 6.85it/s]
reward: -1.6922, last reward: -0.0004, gradient norm: 0.2423: 63%|######2 | 391/625 [00:56<00:34, 6.85it/s]
reward: -1.6922, last reward: -0.0004, gradient norm: 0.2423: 63%|######2 | 392/625 [00:56<00:33, 6.86it/s]
reward: -1.9115, last reward: -0.2602, gradient norm: 2.599: 63%|######2 | 392/625 [00:57<00:33, 6.86it/s]
reward: -1.9115, last reward: -0.2602, gradient norm: 2.599: 63%|######2 | 393/625 [00:57<00:33, 6.91it/s]
reward: -2.2449, last reward: -0.0783, gradient norm: 5.199: 63%|######2 | 393/625 [00:57<00:33, 6.91it/s]
reward: -2.2449, last reward: -0.0783, gradient norm: 5.199: 63%|######3 | 394/625 [00:57<00:33, 6.89it/s]
reward: -2.0631, last reward: -0.0057, gradient norm: 0.7444: 63%|######3 | 394/625 [00:57<00:33, 6.89it/s]
reward: -2.0631, last reward: -0.0057, gradient norm: 0.7444: 63%|######3 | 395/625 [00:57<00:33, 6.87it/s]
reward: -2.3339, last reward: -0.0167, gradient norm: 1.39: 63%|######3 | 395/625 [00:57<00:33, 6.87it/s]
reward: -2.3339, last reward: -0.0167, gradient norm: 1.39: 63%|######3 | 396/625 [00:57<00:33, 6.85it/s]
reward: -2.4806, last reward: -0.0023, gradient norm: 2.317: 63%|######3 | 396/625 [00:57<00:33, 6.85it/s]
reward: -2.4806, last reward: -0.0023, gradient norm: 2.317: 64%|######3 | 397/625 [00:57<00:33, 6.84it/s]
reward: -2.4171, last reward: -0.1438, gradient norm: 5.067: 64%|######3 | 397/625 [00:57<00:33, 6.84it/s]
reward: -2.4171, last reward: -0.1438, gradient norm: 5.067: 64%|######3 | 398/625 [00:57<00:33, 6.82it/s]
reward: -2.2618, last reward: -0.5809, gradient norm: 20.39: 64%|######3 | 398/625 [00:57<00:33, 6.82it/s]
reward: -2.2618, last reward: -0.5809, gradient norm: 20.39: 64%|######3 | 399/625 [00:57<00:33, 6.82it/s]
reward: -2.0115, last reward: -0.0054, gradient norm: 0.3364: 64%|######3 | 399/625 [00:58<00:33, 6.82it/s]
reward: -2.0115, last reward: -0.0054, gradient norm: 0.3364: 64%|######4 | 400/625 [00:58<00:33, 6.82it/s]
reward: -1.8733, last reward: -0.0184, gradient norm: 2.275: 64%|######4 | 400/625 [00:58<00:33, 6.82it/s]
reward: -1.8733, last reward: -0.0184, gradient norm: 2.275: 64%|######4 | 401/625 [00:58<00:32, 6.80it/s]
reward: -1.9137, last reward: -0.0113, gradient norm: 1.025: 64%|######4 | 401/625 [00:58<00:32, 6.80it/s]
reward: -1.9137, last reward: -0.0113, gradient norm: 1.025: 64%|######4 | 402/625 [00:58<00:32, 6.78it/s]
reward: -2.0386, last reward: -0.0625, gradient norm: 2.763: 64%|######4 | 402/625 [00:58<00:32, 6.78it/s]
reward: -2.0386, last reward: -0.0625, gradient norm: 2.763: 64%|######4 | 403/625 [00:58<00:32, 6.78it/s]
reward: -2.1332, last reward: -0.0582, gradient norm: 0.7816: 64%|######4 | 403/625 [00:58<00:32, 6.78it/s]
reward: -2.1332, last reward: -0.0582, gradient norm: 0.7816: 65%|######4 | 404/625 [00:58<00:32, 6.77it/s]
reward: -1.8341, last reward: -0.0941, gradient norm: 5.854: 65%|######4 | 404/625 [00:58<00:32, 6.77it/s]
reward: -1.8341, last reward: -0.0941, gradient norm: 5.854: 65%|######4 | 405/625 [00:58<00:32, 6.79it/s]
reward: -1.8615, last reward: -0.0968, gradient norm: 4.588: 65%|######4 | 405/625 [00:59<00:32, 6.79it/s]
reward: -1.8615, last reward: -0.0968, gradient norm: 4.588: 65%|######4 | 406/625 [00:59<00:31, 6.87it/s]
reward: -2.0981, last reward: -0.3849, gradient norm: 6.008: 65%|######4 | 406/625 [00:59<00:31, 6.87it/s]
reward: -2.0981, last reward: -0.3849, gradient norm: 6.008: 65%|######5 | 407/625 [00:59<00:31, 6.87it/s]
reward: -1.9395, last reward: -0.0765, gradient norm: 4.055: 65%|######5 | 407/625 [00:59<00:31, 6.87it/s]
reward: -1.9395, last reward: -0.0765, gradient norm: 4.055: 65%|######5 | 408/625 [00:59<00:31, 6.91it/s]
reward: -2.2685, last reward: -0.2235, gradient norm: 1.688: 65%|######5 | 408/625 [00:59<00:31, 6.91it/s]
reward: -2.2685, last reward: -0.2235, gradient norm: 1.688: 65%|######5 | 409/625 [00:59<00:31, 6.91it/s]
reward: -2.3052, last reward: -1.4249, gradient norm: 25.99: 65%|######5 | 409/625 [00:59<00:31, 6.91it/s]
reward: -2.3052, last reward: -1.4249, gradient norm: 25.99: 66%|######5 | 410/625 [00:59<00:31, 6.88it/s]
reward: -2.6806, last reward: -1.6383, gradient norm: 30.59: 66%|######5 | 410/625 [00:59<00:31, 6.88it/s]
reward: -2.6806, last reward: -1.6383, gradient norm: 30.59: 66%|######5 | 411/625 [00:59<00:31, 6.88it/s]
reward: -2.3721, last reward: -2.9981, gradient norm: 74.37: 66%|######5 | 411/625 [00:59<00:31, 6.88it/s]
reward: -2.3721, last reward: -2.9981, gradient norm: 74.37: 66%|######5 | 412/625 [00:59<00:31, 6.86it/s]
reward: -2.1862, last reward: -0.0063, gradient norm: 1.822: 66%|######5 | 412/625 [01:00<00:31, 6.86it/s]
reward: -2.1862, last reward: -0.0063, gradient norm: 1.822: 66%|######6 | 413/625 [01:00<00:30, 6.87it/s]
reward: -1.9811, last reward: -0.0171, gradient norm: 1.013: 66%|######6 | 413/625 [01:00<00:30, 6.87it/s]
reward: -1.9811, last reward: -0.0171, gradient norm: 1.013: 66%|######6 | 414/625 [01:00<00:30, 6.86it/s]
reward: -2.0252, last reward: -0.0049, gradient norm: 0.6205: 66%|######6 | 414/625 [01:00<00:30, 6.86it/s]
reward: -2.0252, last reward: -0.0049, gradient norm: 0.6205: 66%|######6 | 415/625 [01:00<00:30, 6.86it/s]
reward: -2.1108, last reward: -0.4921, gradient norm: 23.74: 66%|######6 | 415/625 [01:00<00:30, 6.86it/s]
reward: -2.1108, last reward: -0.4921, gradient norm: 23.74: 67%|######6 | 416/625 [01:00<00:30, 6.85it/s]
reward: -1.9142, last reward: -0.8130, gradient norm: 52.65: 67%|######6 | 416/625 [01:00<00:30, 6.85it/s]
reward: -1.9142, last reward: -0.8130, gradient norm: 52.65: 67%|######6 | 417/625 [01:00<00:30, 6.85it/s]
reward: -2.1725, last reward: -0.0036, gradient norm: 0.3196: 67%|######6 | 417/625 [01:00<00:30, 6.85it/s]
reward: -2.1725, last reward: -0.0036, gradient norm: 0.3196: 67%|######6 | 418/625 [01:00<00:30, 6.86it/s]
reward: -1.7795, last reward: -0.0242, gradient norm: 1.799: 67%|######6 | 418/625 [01:00<00:30, 6.86it/s]
reward: -1.7795, last reward: -0.0242, gradient norm: 1.799: 67%|######7 | 419/625 [01:00<00:30, 6.84it/s]
reward: -1.7737, last reward: -0.0138, gradient norm: 1.39: 67%|######7 | 419/625 [01:01<00:30, 6.84it/s]
reward: -1.7737, last reward: -0.0138, gradient norm: 1.39: 67%|######7 | 420/625 [01:01<00:29, 6.83it/s]
reward: -2.1462, last reward: -0.0053, gradient norm: 0.47: 67%|######7 | 420/625 [01:01<00:29, 6.83it/s]
reward: -2.1462, last reward: -0.0053, gradient norm: 0.47: 67%|######7 | 421/625 [01:01<00:29, 6.84it/s]
reward: -1.9226, last reward: -0.6139, gradient norm: 40.3: 67%|######7 | 421/625 [01:01<00:29, 6.84it/s]
reward: -1.9226, last reward: -0.6139, gradient norm: 40.3: 68%|######7 | 422/625 [01:01<00:29, 6.85it/s]
reward: -1.9889, last reward: -0.0403, gradient norm: 1.112: 68%|######7 | 422/625 [01:01<00:29, 6.85it/s]
reward: -1.9889, last reward: -0.0403, gradient norm: 1.112: 68%|######7 | 423/625 [01:01<00:29, 6.84it/s]
reward: -1.6194, last reward: -0.0032, gradient norm: 0.79: 68%|######7 | 423/625 [01:01<00:29, 6.84it/s]
reward: -1.6194, last reward: -0.0032, gradient norm: 0.79: 68%|######7 | 424/625 [01:01<00:29, 6.82it/s]
reward: -2.3989, last reward: -0.0104, gradient norm: 1.134: 68%|######7 | 424/625 [01:01<00:29, 6.82it/s]
reward: -2.3989, last reward: -0.0104, gradient norm: 1.134: 68%|######8 | 425/625 [01:01<00:29, 6.81it/s]
reward: -1.9960, last reward: -0.0009, gradient norm: 0.6009: 68%|######8 | 425/625 [01:01<00:29, 6.81it/s]
reward: -1.9960, last reward: -0.0009, gradient norm: 0.6009: 68%|######8 | 426/625 [01:01<00:29, 6.80it/s]
reward: -2.2697, last reward: -0.0914, gradient norm: 2.905: 68%|######8 | 426/625 [01:02<00:29, 6.80it/s]
reward: -2.2697, last reward: -0.0914, gradient norm: 2.905: 68%|######8 | 427/625 [01:02<00:29, 6.80it/s]
reward: -2.4256, last reward: -0.1114, gradient norm: 2.102: 68%|######8 | 427/625 [01:02<00:29, 6.80it/s]
reward: -2.4256, last reward: -0.1114, gradient norm: 2.102: 68%|######8 | 428/625 [01:02<00:28, 6.80it/s]
reward: -1.9862, last reward: -0.1932, gradient norm: 22.44: 68%|######8 | 428/625 [01:02<00:28, 6.80it/s]
reward: -1.9862, last reward: -0.1932, gradient norm: 22.44: 69%|######8 | 429/625 [01:02<00:28, 6.80it/s]
reward: -2.0637, last reward: -0.0623, gradient norm: 3.082: 69%|######8 | 429/625 [01:02<00:28, 6.80it/s]
reward: -2.0637, last reward: -0.0623, gradient norm: 3.082: 69%|######8 | 430/625 [01:02<00:28, 6.79it/s]
reward: -1.9906, last reward: -0.2031, gradient norm: 5.5: 69%|######8 | 430/625 [01:02<00:28, 6.79it/s]
reward: -1.9906, last reward: -0.2031, gradient norm: 5.5: 69%|######8 | 431/625 [01:02<00:28, 6.78it/s]
reward: -1.9948, last reward: -0.0895, gradient norm: 3.456: 69%|######8 | 431/625 [01:02<00:28, 6.78it/s]
reward: -1.9948, last reward: -0.0895, gradient norm: 3.456: 69%|######9 | 432/625 [01:02<00:28, 6.78it/s]
reward: -2.1970, last reward: -0.0256, gradient norm: 1.593: 69%|######9 | 432/625 [01:02<00:28, 6.78it/s]
reward: -2.1970, last reward: -0.0256, gradient norm: 1.593: 69%|######9 | 433/625 [01:02<00:28, 6.78it/s]
reward: -2.4231, last reward: -0.0449, gradient norm: 3.644: 69%|######9 | 433/625 [01:03<00:28, 6.78it/s]
reward: -2.4231, last reward: -0.0449, gradient norm: 3.644: 69%|######9 | 434/625 [01:03<00:28, 6.78it/s]
reward: -2.1039, last reward: -3.1973, gradient norm: 87.37: 69%|######9 | 434/625 [01:03<00:28, 6.78it/s]
reward: -2.1039, last reward: -3.1973, gradient norm: 87.37: 70%|######9 | 435/625 [01:03<00:28, 6.78it/s]
reward: -2.4561, last reward: -0.1225, gradient norm: 6.119: 70%|######9 | 435/625 [01:03<00:28, 6.78it/s]
reward: -2.4561, last reward: -0.1225, gradient norm: 6.119: 70%|######9 | 436/625 [01:03<00:27, 6.79it/s]
reward: -2.0211, last reward: -0.2125, gradient norm: 2.94: 70%|######9 | 436/625 [01:03<00:27, 6.79it/s]
reward: -2.0211, last reward: -0.2125, gradient norm: 2.94: 70%|######9 | 437/625 [01:03<00:27, 6.79it/s]
reward: -2.3866, last reward: -0.0050, gradient norm: 0.7202: 70%|######9 | 437/625 [01:03<00:27, 6.79it/s]
reward: -2.3866, last reward: -0.0050, gradient norm: 0.7202: 70%|####### | 438/625 [01:03<00:27, 6.79it/s]
reward: -1.6388, last reward: -0.0072, gradient norm: 0.8657: 70%|####### | 438/625 [01:03<00:27, 6.79it/s]
reward: -1.6388, last reward: -0.0072, gradient norm: 0.8657: 70%|####### | 439/625 [01:03<00:27, 6.79it/s]
reward: -2.1187, last reward: -0.0015, gradient norm: 0.5116: 70%|####### | 439/625 [01:04<00:27, 6.79it/s]
reward: -2.1187, last reward: -0.0015, gradient norm: 0.5116: 70%|####### | 440/625 [01:04<00:27, 6.80it/s]
reward: -2.0432, last reward: -0.0025, gradient norm: 0.7809: 70%|####### | 440/625 [01:04<00:27, 6.80it/s]
reward: -2.0432, last reward: -0.0025, gradient norm: 0.7809: 71%|####### | 441/625 [01:04<00:27, 6.80it/s]
reward: -2.1925, last reward: -0.0103, gradient norm: 2.83: 71%|####### | 441/625 [01:04<00:27, 6.80it/s]
reward: -2.1925, last reward: -0.0103, gradient norm: 2.83: 71%|####### | 442/625 [01:04<00:26, 6.84it/s]
reward: -1.9570, last reward: -0.0002, gradient norm: 0.35: 71%|####### | 442/625 [01:04<00:26, 6.84it/s]
reward: -1.9570, last reward: -0.0002, gradient norm: 0.35: 71%|####### | 443/625 [01:04<00:26, 6.88it/s]
reward: -2.0871, last reward: -0.0022, gradient norm: 0.5601: 71%|####### | 443/625 [01:04<00:26, 6.88it/s]
reward: -2.0871, last reward: -0.0022, gradient norm: 0.5601: 71%|#######1 | 444/625 [01:04<00:26, 6.90it/s]
reward: -2.0165, last reward: -0.0047, gradient norm: 0.6061: 71%|#######1 | 444/625 [01:04<00:26, 6.90it/s]
reward: -2.0165, last reward: -0.0047, gradient norm: 0.6061: 71%|#######1 | 445/625 [01:04<00:26, 6.86it/s]
reward: -2.2746, last reward: -0.0027, gradient norm: 0.7887: 71%|#######1 | 445/625 [01:04<00:26, 6.86it/s]
reward: -2.2746, last reward: -0.0027, gradient norm: 0.7887: 71%|#######1 | 446/625 [01:04<00:26, 6.85it/s]
reward: -2.1835, last reward: -0.0035, gradient norm: 0.855: 71%|#######1 | 446/625 [01:05<00:26, 6.85it/s]
reward: -2.1835, last reward: -0.0035, gradient norm: 0.855: 72%|#######1 | 447/625 [01:05<00:26, 6.84it/s]
reward: -1.8420, last reward: -0.0103, gradient norm: 1.548: 72%|#######1 | 447/625 [01:05<00:26, 6.84it/s]
reward: -1.8420, last reward: -0.0103, gradient norm: 1.548: 72%|#######1 | 448/625 [01:05<00:25, 6.82it/s]
reward: -2.2653, last reward: -0.0126, gradient norm: 0.9736: 72%|#######1 | 448/625 [01:05<00:25, 6.82it/s]
reward: -2.2653, last reward: -0.0126, gradient norm: 0.9736: 72%|#######1 | 449/625 [01:05<00:25, 6.82it/s]
reward: -2.0594, last reward: -0.0119, gradient norm: 0.6196: 72%|#######1 | 449/625 [01:05<00:25, 6.82it/s]
reward: -2.0594, last reward: -0.0119, gradient norm: 0.6196: 72%|#######2 | 450/625 [01:05<00:25, 6.81it/s]
reward: -2.4509, last reward: -0.0373, gradient norm: 11.44: 72%|#######2 | 450/625 [01:05<00:25, 6.81it/s]
reward: -2.4509, last reward: -0.0373, gradient norm: 11.44: 72%|#######2 | 451/625 [01:05<00:25, 6.80it/s]
reward: -2.2528, last reward: -0.0620, gradient norm: 3.992: 72%|#######2 | 451/625 [01:05<00:25, 6.80it/s]
reward: -2.2528, last reward: -0.0620, gradient norm: 3.992: 72%|#######2 | 452/625 [01:05<00:25, 6.80it/s]
reward: -1.6898, last reward: -0.3235, gradient norm: 6.687: 72%|#######2 | 452/625 [01:05<00:25, 6.80it/s]
reward: -1.6898, last reward: -0.3235, gradient norm: 6.687: 72%|#######2 | 453/625 [01:05<00:25, 6.80it/s]
reward: -1.5879, last reward: -0.0905, gradient norm: 2.84: 72%|#######2 | 453/625 [01:06<00:25, 6.80it/s]
reward: -1.5879, last reward: -0.0905, gradient norm: 2.84: 73%|#######2 | 454/625 [01:06<00:25, 6.80it/s]
reward: -1.8406, last reward: -0.0694, gradient norm: 2.288: 73%|#######2 | 454/625 [01:06<00:25, 6.80it/s]
reward: -1.8406, last reward: -0.0694, gradient norm: 2.288: 73%|#######2 | 455/625 [01:06<00:25, 6.79it/s]
reward: -1.8259, last reward: -0.0235, gradient norm: 1.304: 73%|#######2 | 455/625 [01:06<00:25, 6.79it/s]
reward: -1.8259, last reward: -0.0235, gradient norm: 1.304: 73%|#######2 | 456/625 [01:06<00:24, 6.79it/s]
reward: -1.8500, last reward: -0.0024, gradient norm: 1.416: 73%|#######2 | 456/625 [01:06<00:24, 6.79it/s]
reward: -1.8500, last reward: -0.0024, gradient norm: 1.416: 73%|#######3 | 457/625 [01:06<00:24, 6.78it/s]
reward: -1.9649, last reward: -0.4054, gradient norm: 39.3: 73%|#######3 | 457/625 [01:06<00:24, 6.78it/s]
reward: -1.9649, last reward: -0.4054, gradient norm: 39.3: 73%|#######3 | 458/625 [01:06<00:24, 6.78it/s]
reward: -2.2027, last reward: -0.0894, gradient norm: 4.275: 73%|#######3 | 458/625 [01:06<00:24, 6.78it/s]
reward: -2.2027, last reward: -0.0894, gradient norm: 4.275: 73%|#######3 | 459/625 [01:06<00:24, 6.78it/s]
reward: -1.5966, last reward: -0.0113, gradient norm: 1.368: 73%|#######3 | 459/625 [01:06<00:24, 6.78it/s]
reward: -1.5966, last reward: -0.0113, gradient norm: 1.368: 74%|#######3 | 460/625 [01:06<00:24, 6.78it/s]
reward: -1.6942, last reward: -0.0016, gradient norm: 0.4254: 74%|#######3 | 460/625 [01:07<00:24, 6.78it/s]
reward: -1.6942, last reward: -0.0016, gradient norm: 0.4254: 74%|#######3 | 461/625 [01:07<00:24, 6.78it/s]
reward: -1.6703, last reward: -0.0145, gradient norm: 2.142: 74%|#######3 | 461/625 [01:07<00:24, 6.78it/s]
reward: -1.6703, last reward: -0.0145, gradient norm: 2.142: 74%|#######3 | 462/625 [01:07<00:24, 6.78it/s]
reward: -1.8124, last reward: -0.0218, gradient norm: 0.9196: 74%|#######3 | 462/625 [01:07<00:24, 6.78it/s]
reward: -1.8124, last reward: -0.0218, gradient norm: 0.9196: 74%|#######4 | 463/625 [01:07<00:23, 6.78it/s]
reward: -1.8657, last reward: -0.0188, gradient norm: 0.8986: 74%|#######4 | 463/625 [01:07<00:23, 6.78it/s]
reward: -1.8657, last reward: -0.0188, gradient norm: 0.8986: 74%|#######4 | 464/625 [01:07<00:23, 6.78it/s]
reward: -2.0884, last reward: -0.0084, gradient norm: 0.5624: 74%|#######4 | 464/625 [01:07<00:23, 6.78it/s]
reward: -2.0884, last reward: -0.0084, gradient norm: 0.5624: 74%|#######4 | 465/625 [01:07<00:23, 6.80it/s]
reward: -1.8862, last reward: -0.0006, gradient norm: 0.5384: 74%|#######4 | 465/625 [01:07<00:23, 6.80it/s]
reward: -1.8862, last reward: -0.0006, gradient norm: 0.5384: 75%|#######4 | 466/625 [01:07<00:23, 6.82it/s]
reward: -2.1973, last reward: -0.0022, gradient norm: 0.5837: 75%|#######4 | 466/625 [01:07<00:23, 6.82it/s]
reward: -2.1973, last reward: -0.0022, gradient norm: 0.5837: 75%|#######4 | 467/625 [01:07<00:23, 6.87it/s]
reward: -1.8954, last reward: -0.0101, gradient norm: 0.6751: 75%|#######4 | 467/625 [01:08<00:23, 6.87it/s]
reward: -1.8954, last reward: -0.0101, gradient norm: 0.6751: 75%|#######4 | 468/625 [01:08<00:22, 6.87it/s]
reward: -1.8063, last reward: -0.0122, gradient norm: 0.9635: 75%|#######4 | 468/625 [01:08<00:22, 6.87it/s]
reward: -1.8063, last reward: -0.0122, gradient norm: 0.9635: 75%|#######5 | 469/625 [01:08<00:22, 6.93it/s]
reward: -2.0692, last reward: -0.0027, gradient norm: 0.4216: 75%|#######5 | 469/625 [01:08<00:22, 6.93it/s]
reward: -2.0692, last reward: -0.0027, gradient norm: 0.4216: 75%|#######5 | 470/625 [01:08<00:22, 6.96it/s]
reward: -2.1227, last reward: -0.0586, gradient norm: 3.162e+03: 75%|#######5 | 470/625 [01:08<00:22, 6.96it/s]
reward: -2.1227, last reward: -0.0586, gradient norm: 3.162e+03: 75%|#######5 | 471/625 [01:08<00:22, 6.99it/s]
reward: -1.9690, last reward: -0.0074, gradient norm: 0.4166: 75%|#######5 | 471/625 [01:08<00:22, 6.99it/s]
reward: -1.9690, last reward: -0.0074, gradient norm: 0.4166: 76%|#######5 | 472/625 [01:08<00:21, 6.99it/s]
reward: -2.6324, last reward: -0.0119, gradient norm: 1.345: 76%|#######5 | 472/625 [01:08<00:21, 6.99it/s]
reward: -2.6324, last reward: -0.0119, gradient norm: 1.345: 76%|#######5 | 473/625 [01:08<00:21, 6.96it/s]
reward: -2.0778, last reward: -0.0098, gradient norm: 1.166: 76%|#######5 | 473/625 [01:08<00:21, 6.96it/s]
reward: -2.0778, last reward: -0.0098, gradient norm: 1.166: 76%|#######5 | 474/625 [01:08<00:21, 6.98it/s]
reward: -1.8548, last reward: -0.0017, gradient norm: 0.4408: 76%|#######5 | 474/625 [01:09<00:21, 6.98it/s]
reward: -1.8548, last reward: -0.0017, gradient norm: 0.4408: 76%|#######6 | 475/625 [01:09<00:21, 7.00it/s]
reward: -1.8125, last reward: -0.0003, gradient norm: 0.1515: 76%|#######6 | 475/625 [01:09<00:21, 7.00it/s]
reward: -1.8125, last reward: -0.0003, gradient norm: 0.1515: 76%|#######6 | 476/625 [01:09<00:21, 7.01it/s]
reward: -2.2733, last reward: -0.0044, gradient norm: 0.2836: 76%|#######6 | 476/625 [01:09<00:21, 7.01it/s]
reward: -2.2733, last reward: -0.0044, gradient norm: 0.2836: 76%|#######6 | 477/625 [01:09<00:21, 6.95it/s]
reward: -1.7497, last reward: -0.0149, gradient norm: 0.7681: 76%|#######6 | 477/625 [01:09<00:21, 6.95it/s]
reward: -1.7497, last reward: -0.0149, gradient norm: 0.7681: 76%|#######6 | 478/625 [01:09<00:21, 6.91it/s]
reward: -1.8547, last reward: -0.0105, gradient norm: 0.7212: 76%|#######6 | 478/625 [01:09<00:21, 6.91it/s]
reward: -1.8547, last reward: -0.0105, gradient norm: 0.7212: 77%|#######6 | 479/625 [01:09<00:21, 6.87it/s]
reward: -1.9848, last reward: -0.0019, gradient norm: 0.6498: 77%|#######6 | 479/625 [01:09<00:21, 6.87it/s]
reward: -1.9848, last reward: -0.0019, gradient norm: 0.6498: 77%|#######6 | 480/625 [01:09<00:21, 6.84it/s]
reward: -2.1987, last reward: -0.0011, gradient norm: 0.5473: 77%|#######6 | 480/625 [01:09<00:21, 6.84it/s]
reward: -2.1987, last reward: -0.0011, gradient norm: 0.5473: 77%|#######6 | 481/625 [01:09<00:21, 6.82it/s]
reward: -1.8991, last reward: -0.0033, gradient norm: 0.6091: 77%|#######6 | 481/625 [01:10<00:21, 6.82it/s]
reward: -1.8991, last reward: -0.0033, gradient norm: 0.6091: 77%|#######7 | 482/625 [01:10<00:20, 6.81it/s]
reward: -1.9189, last reward: -0.0032, gradient norm: 0.5771: 77%|#######7 | 482/625 [01:10<00:20, 6.81it/s]
reward: -1.9189, last reward: -0.0032, gradient norm: 0.5771: 77%|#######7 | 483/625 [01:10<00:20, 6.82it/s]
reward: -1.6781, last reward: -0.0004, gradient norm: 0.7542: 77%|#######7 | 483/625 [01:10<00:20, 6.82it/s]
reward: -1.6781, last reward: -0.0004, gradient norm: 0.7542: 77%|#######7 | 484/625 [01:10<00:20, 6.81it/s]
reward: -1.5959, last reward: -0.0064, gradient norm: 0.4295: 77%|#######7 | 484/625 [01:10<00:20, 6.81it/s]
reward: -1.5959, last reward: -0.0064, gradient norm: 0.4295: 78%|#######7 | 485/625 [01:10<00:20, 6.81it/s]
reward: -2.2547, last reward: -0.0103, gradient norm: 0.4641: 78%|#######7 | 485/625 [01:10<00:20, 6.81it/s]
reward: -2.2547, last reward: -0.0103, gradient norm: 0.4641: 78%|#######7 | 486/625 [01:10<00:20, 6.80it/s]
reward: -2.1509, last reward: -0.0636, gradient norm: 6.547: 78%|#######7 | 486/625 [01:10<00:20, 6.80it/s]
reward: -2.1509, last reward: -0.0636, gradient norm: 6.547: 78%|#######7 | 487/625 [01:10<00:20, 6.81it/s]
reward: -2.0972, last reward: -0.0065, gradient norm: 0.2593: 78%|#######7 | 487/625 [01:11<00:20, 6.81it/s]
reward: -2.0972, last reward: -0.0065, gradient norm: 0.2593: 78%|#######8 | 488/625 [01:11<00:20, 6.81it/s]
reward: -2.1694, last reward: -0.0083, gradient norm: 0.5759: 78%|#######8 | 488/625 [01:11<00:20, 6.81it/s]
reward: -2.1694, last reward: -0.0083, gradient norm: 0.5759: 78%|#######8 | 489/625 [01:11<00:19, 6.81it/s]
reward: -2.0493, last reward: -0.0021, gradient norm: 0.7805: 78%|#######8 | 489/625 [01:11<00:19, 6.81it/s]
reward: -2.0493, last reward: -0.0021, gradient norm: 0.7805: 78%|#######8 | 490/625 [01:11<00:19, 6.82it/s]
reward: -2.0950, last reward: -0.0021, gradient norm: 0.497: 78%|#######8 | 490/625 [01:11<00:19, 6.82it/s]
reward: -2.0950, last reward: -0.0021, gradient norm: 0.497: 79%|#######8 | 491/625 [01:11<00:19, 6.81it/s]
reward: -1.9717, last reward: -0.0012, gradient norm: 0.3672: 79%|#######8 | 491/625 [01:11<00:19, 6.81it/s]
reward: -1.9717, last reward: -0.0012, gradient norm: 0.3672: 79%|#######8 | 492/625 [01:11<00:19, 6.81it/s]
reward: -2.0207, last reward: -0.0009, gradient norm: 0.331: 79%|#######8 | 492/625 [01:11<00:19, 6.81it/s]
reward: -2.0207, last reward: -0.0009, gradient norm: 0.331: 79%|#######8 | 493/625 [01:11<00:19, 6.80it/s]
reward: -1.8266, last reward: -0.0069, gradient norm: 0.5365: 79%|#######8 | 493/625 [01:11<00:19, 6.80it/s]
reward: -1.8266, last reward: -0.0069, gradient norm: 0.5365: 79%|#######9 | 494/625 [01:11<00:19, 6.81it/s]
reward: -2.2623, last reward: -0.0065, gradient norm: 0.5078: 79%|#######9 | 494/625 [01:12<00:19, 6.81it/s]
reward: -2.2623, last reward: -0.0065, gradient norm: 0.5078: 79%|#######9 | 495/625 [01:12<00:19, 6.81it/s]
reward: -2.0230, last reward: -0.0027, gradient norm: 0.4545: 79%|#######9 | 495/625 [01:12<00:19, 6.81it/s]
reward: -2.0230, last reward: -0.0027, gradient norm: 0.4545: 79%|#######9 | 496/625 [01:12<00:18, 6.81it/s]
reward: -1.6047, last reward: -0.0000, gradient norm: 0.09636: 79%|#######9 | 496/625 [01:12<00:18, 6.81it/s]
reward: -1.6047, last reward: -0.0000, gradient norm: 0.09636: 80%|#######9 | 497/625 [01:12<00:18, 6.82it/s]
reward: -1.8754, last reward: -0.0010, gradient norm: 0.2: 80%|#######9 | 497/625 [01:12<00:18, 6.82it/s]
reward: -1.8754, last reward: -0.0010, gradient norm: 0.2: 80%|#######9 | 498/625 [01:12<00:18, 6.81it/s]
reward: -2.6216, last reward: -0.0031, gradient norm: 0.8269: 80%|#######9 | 498/625 [01:12<00:18, 6.81it/s]
reward: -2.6216, last reward: -0.0031, gradient norm: 0.8269: 80%|#######9 | 499/625 [01:12<00:18, 6.80it/s]
reward: -1.7361, last reward: -0.0023, gradient norm: 0.4082: 80%|#######9 | 499/625 [01:12<00:18, 6.80it/s]
reward: -1.7361, last reward: -0.0023, gradient norm: 0.4082: 80%|######## | 500/625 [01:12<00:18, 6.77it/s]
reward: -1.6642, last reward: -0.0006, gradient norm: 0.2284: 80%|######## | 500/625 [01:12<00:18, 6.77it/s]
reward: -1.6642, last reward: -0.0006, gradient norm: 0.2284: 80%|######## | 501/625 [01:12<00:18, 6.70it/s]
reward: -1.9130, last reward: -0.0008, gradient norm: 0.3031: 80%|######## | 501/625 [01:13<00:18, 6.70it/s]
reward: -1.9130, last reward: -0.0008, gradient norm: 0.3031: 80%|######## | 502/625 [01:13<00:18, 6.71it/s]
reward: -2.2944, last reward: -0.0035, gradient norm: 0.2986: 80%|######## | 502/625 [01:13<00:18, 6.71it/s]
reward: -2.2944, last reward: -0.0035, gradient norm: 0.2986: 80%|######## | 503/625 [01:13<00:18, 6.77it/s]
reward: -1.7624, last reward: -0.0056, gradient norm: 0.3858: 80%|######## | 503/625 [01:13<00:18, 6.77it/s]
reward: -1.7624, last reward: -0.0056, gradient norm: 0.3858: 81%|######## | 504/625 [01:13<00:17, 6.84it/s]
reward: -2.0890, last reward: -0.0042, gradient norm: 0.38: 81%|######## | 504/625 [01:13<00:17, 6.84it/s]
reward: -2.0890, last reward: -0.0042, gradient norm: 0.38: 81%|######## | 505/625 [01:13<00:17, 6.90it/s]
reward: -1.7505, last reward: -0.0017, gradient norm: 0.2157: 81%|######## | 505/625 [01:13<00:17, 6.90it/s]
reward: -1.7505, last reward: -0.0017, gradient norm: 0.2157: 81%|######## | 506/625 [01:13<00:17, 6.93it/s]
reward: -1.8394, last reward: -0.0013, gradient norm: 0.3413: 81%|######## | 506/625 [01:13<00:17, 6.93it/s]
reward: -1.8394, last reward: -0.0013, gradient norm: 0.3413: 81%|########1 | 507/625 [01:13<00:16, 6.95it/s]
reward: -1.9609, last reward: -0.0041, gradient norm: 0.6905: 81%|########1 | 507/625 [01:13<00:16, 6.95it/s]
reward: -1.9609, last reward: -0.0041, gradient norm: 0.6905: 81%|########1 | 508/625 [01:13<00:16, 6.90it/s]
reward: -1.8467, last reward: -0.0011, gradient norm: 0.4409: 81%|########1 | 508/625 [01:14<00:16, 6.90it/s]
reward: -1.8467, last reward: -0.0011, gradient norm: 0.4409: 81%|########1 | 509/625 [01:14<00:16, 6.89it/s]
reward: -2.0252, last reward: -0.0021, gradient norm: 0.213: 81%|########1 | 509/625 [01:14<00:16, 6.89it/s]
reward: -2.0252, last reward: -0.0021, gradient norm: 0.213: 82%|########1 | 510/625 [01:14<00:16, 6.89it/s]
reward: -1.8128, last reward: -0.0073, gradient norm: 0.3559: 82%|########1 | 510/625 [01:14<00:16, 6.89it/s]
reward: -1.8128, last reward: -0.0073, gradient norm: 0.3559: 82%|########1 | 511/625 [01:14<00:16, 6.87it/s]
reward: -2.1479, last reward: -0.0264, gradient norm: 3.68: 82%|########1 | 511/625 [01:14<00:16, 6.87it/s]
reward: -2.1479, last reward: -0.0264, gradient norm: 3.68: 82%|########1 | 512/625 [01:14<00:16, 6.86it/s]
reward: -2.1589, last reward: -0.0025, gradient norm: 5.566: 82%|########1 | 512/625 [01:14<00:16, 6.86it/s]
reward: -2.1589, last reward: -0.0025, gradient norm: 5.566: 82%|########2 | 513/625 [01:14<00:16, 6.86it/s]
reward: -2.2756, last reward: -0.0046, gradient norm: 0.5266: 82%|########2 | 513/625 [01:14<00:16, 6.86it/s]
reward: -2.2756, last reward: -0.0046, gradient norm: 0.5266: 82%|########2 | 514/625 [01:14<00:16, 6.88it/s]
reward: -1.9873, last reward: -0.0112, gradient norm: 0.9314: 82%|########2 | 514/625 [01:14<00:16, 6.88it/s]
reward: -1.9873, last reward: -0.0112, gradient norm: 0.9314: 82%|########2 | 515/625 [01:14<00:15, 6.88it/s]
reward: -2.3791, last reward: -0.0721, gradient norm: 1.14: 82%|########2 | 515/625 [01:15<00:15, 6.88it/s]
reward: -2.3791, last reward: -0.0721, gradient norm: 1.14: 83%|########2 | 516/625 [01:15<00:15, 6.89it/s]
reward: -2.4580, last reward: -0.0758, gradient norm: 0.6114: 83%|########2 | 516/625 [01:15<00:15, 6.89it/s]
reward: -2.4580, last reward: -0.0758, gradient norm: 0.6114: 83%|########2 | 517/625 [01:15<00:15, 6.87it/s]
reward: -1.9748, last reward: -0.0001, gradient norm: 0.2431: 83%|########2 | 517/625 [01:15<00:15, 6.87it/s]
reward: -1.9748, last reward: -0.0001, gradient norm: 0.2431: 83%|########2 | 518/625 [01:15<00:15, 6.86it/s]
reward: -2.1958, last reward: -0.0044, gradient norm: 0.5553: 83%|########2 | 518/625 [01:15<00:15, 6.86it/s]
reward: -2.1958, last reward: -0.0044, gradient norm: 0.5553: 83%|########3 | 519/625 [01:15<00:15, 6.86it/s]
reward: -1.8924, last reward: -0.0097, gradient norm: 17.34: 83%|########3 | 519/625 [01:15<00:15, 6.86it/s]
reward: -1.8924, last reward: -0.0097, gradient norm: 17.34: 83%|########3 | 520/625 [01:15<00:15, 6.85it/s]
reward: -2.3737, last reward: -0.0234, gradient norm: 1.899: 83%|########3 | 520/625 [01:15<00:15, 6.85it/s]
reward: -2.3737, last reward: -0.0234, gradient norm: 1.899: 83%|########3 | 521/625 [01:15<00:15, 6.85it/s]
reward: -1.9125, last reward: -0.0063, gradient norm: 0.4623: 83%|########3 | 521/625 [01:15<00:15, 6.85it/s]
reward: -1.9125, last reward: -0.0063, gradient norm: 0.4623: 84%|########3 | 522/625 [01:15<00:15, 6.85it/s]
reward: -2.3230, last reward: -0.0589, gradient norm: 0.3784: 84%|########3 | 522/625 [01:16<00:15, 6.85it/s]
reward: -2.3230, last reward: -0.0589, gradient norm: 0.3784: 84%|########3 | 523/625 [01:16<00:14, 6.84it/s]
reward: -1.9482, last reward: -0.0051, gradient norm: 1.105: 84%|########3 | 523/625 [01:16<00:14, 6.84it/s]
reward: -1.9482, last reward: -0.0051, gradient norm: 1.105: 84%|########3 | 524/625 [01:16<00:14, 6.86it/s]
reward: -2.1979, last reward: -0.0045, gradient norm: 0.6401: 84%|########3 | 524/625 [01:16<00:14, 6.86it/s]
reward: -2.1979, last reward: -0.0045, gradient norm: 0.6401: 84%|########4 | 525/625 [01:16<00:14, 6.85it/s]
reward: -2.1588, last reward: -0.0048, gradient norm: 0.6255: 84%|########4 | 525/625 [01:16<00:14, 6.85it/s]
reward: -2.1588, last reward: -0.0048, gradient norm: 0.6255: 84%|########4 | 526/625 [01:16<00:14, 6.85it/s]
reward: -1.6084, last reward: -0.0010, gradient norm: 0.3477: 84%|########4 | 526/625 [01:16<00:14, 6.85it/s]
reward: -1.6084, last reward: -0.0010, gradient norm: 0.3477: 84%|########4 | 527/625 [01:16<00:14, 6.87it/s]
reward: -2.1475, last reward: -0.0209, gradient norm: 0.3456: 84%|########4 | 527/625 [01:16<00:14, 6.87it/s]
reward: -2.1475, last reward: -0.0209, gradient norm: 0.3456: 84%|########4 | 528/625 [01:16<00:14, 6.87it/s]
reward: -1.7611, last reward: -0.1040, gradient norm: 18.52: 84%|########4 | 528/625 [01:17<00:14, 6.87it/s]
reward: -1.7611, last reward: -0.1040, gradient norm: 18.52: 85%|########4 | 529/625 [01:17<00:14, 6.86it/s]
reward: -2.0099, last reward: -0.0173, gradient norm: 1.643: 85%|########4 | 529/625 [01:17<00:14, 6.86it/s]
reward: -2.0099, last reward: -0.0173, gradient norm: 1.643: 85%|########4 | 530/625 [01:17<00:13, 6.85it/s]
reward: -2.8189, last reward: -1.4358, gradient norm: 46.61: 85%|########4 | 530/625 [01:17<00:13, 6.85it/s]
reward: -2.8189, last reward: -1.4358, gradient norm: 46.61: 85%|########4 | 531/625 [01:17<00:13, 6.85it/s]
reward: -2.9897, last reward: -2.4869, gradient norm: 51.23: 85%|########4 | 531/625 [01:17<00:13, 6.85it/s]
reward: -2.9897, last reward: -2.4869, gradient norm: 51.23: 85%|########5 | 532/625 [01:17<00:13, 6.85it/s]
reward: -2.1548, last reward: -0.9751, gradient norm: 72.21: 85%|########5 | 532/625 [01:17<00:13, 6.85it/s]
reward: -2.1548, last reward: -0.9751, gradient norm: 72.21: 85%|########5 | 533/625 [01:17<00:13, 6.85it/s]
reward: -1.6362, last reward: -0.0022, gradient norm: 0.7495: 85%|########5 | 533/625 [01:17<00:13, 6.85it/s]
reward: -1.6362, last reward: -0.0022, gradient norm: 0.7495: 85%|########5 | 534/625 [01:17<00:13, 6.85it/s]
reward: -2.1749, last reward: -0.0105, gradient norm: 0.9513: 85%|########5 | 534/625 [01:17<00:13, 6.85it/s]
reward: -2.1749, last reward: -0.0105, gradient norm: 0.9513: 86%|########5 | 535/625 [01:17<00:13, 6.84it/s]
reward: -1.7708, last reward: -0.0371, gradient norm: 1.432: 86%|########5 | 535/625 [01:18<00:13, 6.84it/s]
reward: -1.7708, last reward: -0.0371, gradient norm: 1.432: 86%|########5 | 536/625 [01:18<00:13, 6.83it/s]
reward: -2.2649, last reward: -0.0437, gradient norm: 2.327: 86%|########5 | 536/625 [01:18<00:13, 6.83it/s]
reward: -2.2649, last reward: -0.0437, gradient norm: 2.327: 86%|########5 | 537/625 [01:18<00:12, 6.80it/s]
reward: -2.5491, last reward: -0.0276, gradient norm: 1.246: 86%|########5 | 537/625 [01:18<00:12, 6.80it/s]
reward: -2.5491, last reward: -0.0276, gradient norm: 1.246: 86%|########6 | 538/625 [01:18<00:12, 6.82it/s]
reward: -2.6426, last reward: -0.7294, gradient norm: 1.078e+03: 86%|########6 | 538/625 [01:18<00:12, 6.82it/s]
reward: -2.6426, last reward: -0.7294, gradient norm: 1.078e+03: 86%|########6 | 539/625 [01:18<00:12, 6.83it/s]
reward: -1.9928, last reward: -0.0003, gradient norm: 1.576: 86%|########6 | 539/625 [01:18<00:12, 6.83it/s]
reward: -1.9928, last reward: -0.0003, gradient norm: 1.576: 86%|########6 | 540/625 [01:18<00:12, 6.84it/s]
reward: -1.7937, last reward: -0.0124, gradient norm: 0.9664: 86%|########6 | 540/625 [01:18<00:12, 6.84it/s]
reward: -1.7937, last reward: -0.0124, gradient norm: 0.9664: 87%|########6 | 541/625 [01:18<00:12, 6.85it/s]
reward: -2.3342, last reward: -0.0204, gradient norm: 1.81: 87%|########6 | 541/625 [01:18<00:12, 6.85it/s]
reward: -2.3342, last reward: -0.0204, gradient norm: 1.81: 87%|########6 | 542/625 [01:18<00:12, 6.85it/s]
reward: -2.2046, last reward: -0.0122, gradient norm: 1.004: 87%|########6 | 542/625 [01:19<00:12, 6.85it/s]
reward: -2.2046, last reward: -0.0122, gradient norm: 1.004: 87%|########6 | 543/625 [01:19<00:11, 6.83it/s]
reward: -2.0000, last reward: -0.0014, gradient norm: 0.5496: 87%|########6 | 543/625 [01:19<00:11, 6.83it/s]
reward: -2.0000, last reward: -0.0014, gradient norm: 0.5496: 87%|########7 | 544/625 [01:19<00:11, 6.84it/s]
reward: -2.0956, last reward: -0.0059, gradient norm: 1.425: 87%|########7 | 544/625 [01:19<00:11, 6.84it/s]
reward: -2.0956, last reward: -0.0059, gradient norm: 1.425: 87%|########7 | 545/625 [01:19<00:11, 6.88it/s]
reward: -2.9028, last reward: -0.5843, gradient norm: 21.12: 87%|########7 | 545/625 [01:19<00:11, 6.88it/s]
reward: -2.9028, last reward: -0.5843, gradient norm: 21.12: 87%|########7 | 546/625 [01:19<00:11, 6.87it/s]
reward: -2.0674, last reward: -0.0178, gradient norm: 0.797: 87%|########7 | 546/625 [01:19<00:11, 6.87it/s]
reward: -2.0674, last reward: -0.0178, gradient norm: 0.797: 88%|########7 | 547/625 [01:19<00:11, 6.88it/s]
reward: -2.2815, last reward: -0.0599, gradient norm: 1.227: 88%|########7 | 547/625 [01:19<00:11, 6.88it/s]
reward: -2.2815, last reward: -0.0599, gradient norm: 1.227: 88%|########7 | 548/625 [01:19<00:11, 6.88it/s]
reward: -3.1587, last reward: -0.9276, gradient norm: 20.56: 88%|########7 | 548/625 [01:19<00:11, 6.88it/s]
reward: -3.1587, last reward: -0.9276, gradient norm: 20.56: 88%|########7 | 549/625 [01:19<00:11, 6.87it/s]
reward: -3.8228, last reward: -2.9229, gradient norm: 308.2: 88%|########7 | 549/625 [01:20<00:11, 6.87it/s]
reward: -3.8228, last reward: -2.9229, gradient norm: 308.2: 88%|########8 | 550/625 [01:20<00:10, 6.91it/s]
reward: -1.6164, last reward: -0.0120, gradient norm: 2.259: 88%|########8 | 550/625 [01:20<00:10, 6.91it/s]
reward: -1.6164, last reward: -0.0120, gradient norm: 2.259: 88%|########8 | 551/625 [01:20<00:10, 6.95it/s]
reward: -1.6850, last reward: -0.0227, gradient norm: 0.9167: 88%|########8 | 551/625 [01:20<00:10, 6.95it/s]
reward: -1.6850, last reward: -0.0227, gradient norm: 0.9167: 88%|########8 | 552/625 [01:20<00:10, 6.98it/s]
reward: -2.3092, last reward: -0.0670, gradient norm: 0.9177: 88%|########8 | 552/625 [01:20<00:10, 6.98it/s]
reward: -2.3092, last reward: -0.0670, gradient norm: 0.9177: 88%|########8 | 553/625 [01:20<00:10, 7.00it/s]
reward: -2.1599, last reward: -0.0043, gradient norm: 1.195: 88%|########8 | 553/625 [01:20<00:10, 7.00it/s]
reward: -2.1599, last reward: -0.0043, gradient norm: 1.195: 89%|########8 | 554/625 [01:20<00:10, 7.01it/s]
reward: -2.4672, last reward: -0.0057, gradient norm: 0.6367: 89%|########8 | 554/625 [01:20<00:10, 7.01it/s]
reward: -2.4672, last reward: -0.0057, gradient norm: 0.6367: 89%|########8 | 555/625 [01:20<00:09, 7.02it/s]
reward: -2.3657, last reward: -0.1970, gradient norm: 4.202: 89%|########8 | 555/625 [01:20<00:09, 7.02it/s]
reward: -2.3657, last reward: -0.1970, gradient norm: 4.202: 89%|########8 | 556/625 [01:20<00:09, 7.00it/s]
reward: -2.6694, last reward: -0.1215, gradient norm: 1.324: 89%|########8 | 556/625 [01:21<00:09, 7.00it/s]
reward: -2.6694, last reward: -0.1215, gradient norm: 1.324: 89%|########9 | 557/625 [01:21<00:09, 7.01it/s]
reward: -2.2622, last reward: -0.0372, gradient norm: 0.4841: 89%|########9 | 557/625 [01:21<00:09, 7.01it/s]
reward: -2.2622, last reward: -0.0372, gradient norm: 0.4841: 89%|########9 | 558/625 [01:21<00:09, 7.00it/s]
reward: -2.2707, last reward: -0.0058, gradient norm: 5.757: 89%|########9 | 558/625 [01:21<00:09, 7.00it/s]
reward: -2.2707, last reward: -0.0058, gradient norm: 5.757: 89%|########9 | 559/625 [01:21<00:09, 6.96it/s]
reward: -2.2267, last reward: -0.0014, gradient norm: 0.5415: 89%|########9 | 559/625 [01:21<00:09, 6.96it/s]
reward: -2.2267, last reward: -0.0014, gradient norm: 0.5415: 90%|########9 | 560/625 [01:21<00:09, 6.97it/s]
reward: -2.4556, last reward: -0.0163, gradient norm: 1.146: 90%|########9 | 560/625 [01:21<00:09, 6.97it/s]
reward: -2.4556, last reward: -0.0163, gradient norm: 1.146: 90%|########9 | 561/625 [01:21<00:09, 6.93it/s]
reward: -2.1839, last reward: -0.0809, gradient norm: 0.6262: 90%|########9 | 561/625 [01:21<00:09, 6.93it/s]
reward: -2.1839, last reward: -0.0809, gradient norm: 0.6262: 90%|########9 | 562/625 [01:21<00:09, 6.93it/s]
reward: -2.0278, last reward: -0.0018, gradient norm: 1.327: 90%|########9 | 562/625 [01:21<00:09, 6.93it/s]
reward: -2.0278, last reward: -0.0018, gradient norm: 1.327: 90%|######### | 563/625 [01:21<00:08, 6.91it/s]
reward: -2.1112, last reward: -0.0011, gradient norm: 0.354: 90%|######### | 563/625 [01:22<00:08, 6.91it/s]
reward: -2.1112, last reward: -0.0011, gradient norm: 0.354: 90%|######### | 564/625 [01:22<00:08, 6.94it/s]
reward: -2.6155, last reward: -0.0004, gradient norm: 2.008: 90%|######### | 564/625 [01:22<00:08, 6.94it/s]
reward: -2.6155, last reward: -0.0004, gradient norm: 2.008: 90%|######### | 565/625 [01:22<00:08, 6.94it/s]
reward: -3.1427, last reward: -0.3582, gradient norm: 7.624: 90%|######### | 565/625 [01:22<00:08, 6.94it/s]
reward: -3.1427, last reward: -0.3582, gradient norm: 7.624: 91%|######### | 566/625 [01:22<00:08, 6.94it/s]
reward: -2.7870, last reward: -0.9490, gradient norm: 18.26: 91%|######### | 566/625 [01:22<00:08, 6.94it/s]
reward: -2.7870, last reward: -0.9490, gradient norm: 18.26: 91%|######### | 567/625 [01:22<00:08, 6.93it/s]
reward: -3.0439, last reward: -0.8796, gradient norm: 29.89: 91%|######### | 567/625 [01:22<00:08, 6.93it/s]
reward: -3.0439, last reward: -0.8796, gradient norm: 29.89: 91%|######### | 568/625 [01:22<00:08, 6.89it/s]
reward: -2.8026, last reward: -0.2720, gradient norm: 8.612: 91%|######### | 568/625 [01:22<00:08, 6.89it/s]
reward: -2.8026, last reward: -0.2720, gradient norm: 8.612: 91%|#########1| 569/625 [01:22<00:08, 6.88it/s]
reward: -2.3147, last reward: -0.8486, gradient norm: 41.13: 91%|#########1| 569/625 [01:22<00:08, 6.88it/s]
reward: -2.3147, last reward: -0.8486, gradient norm: 41.13: 91%|#########1| 570/625 [01:22<00:08, 6.87it/s]
reward: -1.7917, last reward: -0.0129, gradient norm: 2.365: 91%|#########1| 570/625 [01:23<00:08, 6.87it/s]
reward: -1.7917, last reward: -0.0129, gradient norm: 2.365: 91%|#########1| 571/625 [01:23<00:07, 6.87it/s]
reward: -1.9553, last reward: -0.0020, gradient norm: 0.6871: 91%|#########1| 571/625 [01:23<00:07, 6.87it/s]
reward: -1.9553, last reward: -0.0020, gradient norm: 0.6871: 92%|#########1| 572/625 [01:23<00:07, 6.86it/s]
reward: -2.3132, last reward: -0.0159, gradient norm: 0.8646: 92%|#########1| 572/625 [01:23<00:07, 6.86it/s]
reward: -2.3132, last reward: -0.0159, gradient norm: 0.8646: 92%|#########1| 573/625 [01:23<00:07, 6.89it/s]
reward: -1.5320, last reward: -0.0269, gradient norm: 1.02: 92%|#########1| 573/625 [01:23<00:07, 6.89it/s]
reward: -1.5320, last reward: -0.0269, gradient norm: 1.02: 92%|#########1| 574/625 [01:23<00:07, 6.88it/s]
reward: -2.2955, last reward: -0.0245, gradient norm: 1.267: 92%|#########1| 574/625 [01:23<00:07, 6.88it/s]
reward: -2.2955, last reward: -0.0245, gradient norm: 1.267: 92%|#########2| 575/625 [01:23<00:07, 6.89it/s]
reward: -2.3347, last reward: -0.0179, gradient norm: 1.528: 92%|#########2| 575/625 [01:23<00:07, 6.89it/s]
reward: -2.3347, last reward: -0.0179, gradient norm: 1.528: 92%|#########2| 576/625 [01:23<00:07, 6.88it/s]
reward: -1.9718, last reward: -0.1629, gradient norm: 8.804: 92%|#########2| 576/625 [01:23<00:07, 6.88it/s]
reward: -1.9718, last reward: -0.1629, gradient norm: 8.804: 92%|#########2| 577/625 [01:23<00:06, 6.87it/s]
reward: -2.4164, last reward: -0.0070, gradient norm: 0.4335: 92%|#########2| 577/625 [01:24<00:06, 6.87it/s]
reward: -2.4164, last reward: -0.0070, gradient norm: 0.4335: 92%|#########2| 578/625 [01:24<00:06, 6.92it/s]
reward: -2.2993, last reward: -0.0011, gradient norm: 1.371: 92%|#########2| 578/625 [01:24<00:06, 6.92it/s]
reward: -2.2993, last reward: -0.0011, gradient norm: 1.371: 93%|#########2| 579/625 [01:24<00:06, 6.93it/s]
reward: -3.3049, last reward: -0.9063, gradient norm: 34.23: 93%|#########2| 579/625 [01:24<00:06, 6.93it/s]
reward: -3.3049, last reward: -0.9063, gradient norm: 34.23: 93%|#########2| 580/625 [01:24<00:06, 6.92it/s]
reward: -2.8785, last reward: -0.3295, gradient norm: 10.91: 93%|#########2| 580/625 [01:24<00:06, 6.92it/s]
reward: -2.8785, last reward: -0.3295, gradient norm: 10.91: 93%|#########2| 581/625 [01:24<00:06, 6.92it/s]
reward: -2.5184, last reward: -0.0546, gradient norm: 21.09: 93%|#########2| 581/625 [01:24<00:06, 6.92it/s]
reward: -2.5184, last reward: -0.0546, gradient norm: 21.09: 93%|#########3| 582/625 [01:24<00:06, 6.91it/s]
reward: -2.4039, last reward: -0.4589, gradient norm: 10.86: 93%|#########3| 582/625 [01:24<00:06, 6.91it/s]
reward: -2.4039, last reward: -0.4589, gradient norm: 10.86: 93%|#########3| 583/625 [01:24<00:06, 6.93it/s]
reward: -2.4697, last reward: -0.2476, gradient norm: 4.689: 93%|#########3| 583/625 [01:24<00:06, 6.93it/s]
reward: -2.4697, last reward: -0.2476, gradient norm: 4.689: 93%|#########3| 584/625 [01:24<00:05, 6.96it/s]
reward: -2.0018, last reward: -0.2397, gradient norm: 8.393: 93%|#########3| 584/625 [01:25<00:05, 6.96it/s]
reward: -2.0018, last reward: -0.2397, gradient norm: 8.393: 94%|#########3| 585/625 [01:25<00:05, 6.98it/s]
reward: -2.4953, last reward: -0.1775, gradient norm: 24.17: 94%|#########3| 585/625 [01:25<00:05, 6.98it/s]
reward: -2.4953, last reward: -0.1775, gradient norm: 24.17: 94%|#########3| 586/625 [01:25<00:05, 6.99it/s]
reward: -2.2258, last reward: -0.0110, gradient norm: 0.7671: 94%|#########3| 586/625 [01:25<00:05, 6.99it/s]
reward: -2.2258, last reward: -0.0110, gradient norm: 0.7671: 94%|#########3| 587/625 [01:25<00:05, 7.00it/s]
reward: -2.3981, last reward: -0.0011, gradient norm: 1.617: 94%|#########3| 587/625 [01:25<00:05, 7.00it/s]
reward: -2.3981, last reward: -0.0011, gradient norm: 1.617: 94%|#########4| 588/625 [01:25<00:05, 7.01it/s]
reward: -1.8590, last reward: -0.0007, gradient norm: 1.131: 94%|#########4| 588/625 [01:25<00:05, 7.01it/s]
reward: -1.8590, last reward: -0.0007, gradient norm: 1.131: 94%|#########4| 589/625 [01:25<00:05, 6.95it/s]
reward: -1.9820, last reward: -0.4221, gradient norm: 49.4: 94%|#########4| 589/625 [01:25<00:05, 6.95it/s]
reward: -1.9820, last reward: -0.4221, gradient norm: 49.4: 94%|#########4| 590/625 [01:25<00:05, 6.95it/s]
reward: -2.1293, last reward: -0.0116, gradient norm: 0.868: 94%|#########4| 590/625 [01:25<00:05, 6.95it/s]
reward: -2.1293, last reward: -0.0116, gradient norm: 0.868: 95%|#########4| 591/625 [01:25<00:04, 6.93it/s]
reward: -2.1675, last reward: -0.0173, gradient norm: 0.5931: 95%|#########4| 591/625 [01:26<00:04, 6.93it/s]
reward: -2.1675, last reward: -0.0173, gradient norm: 0.5931: 95%|#########4| 592/625 [01:26<00:04, 6.94it/s]
reward: -2.2910, last reward: -0.0207, gradient norm: 0.5219: 95%|#########4| 592/625 [01:26<00:04, 6.94it/s]
reward: -2.2910, last reward: -0.0207, gradient norm: 0.5219: 95%|#########4| 593/625 [01:26<00:04, 6.95it/s]
reward: -2.2124, last reward: -0.1730, gradient norm: 5.737: 95%|#########4| 593/625 [01:26<00:04, 6.95it/s]
reward: -2.2124, last reward: -0.1730, gradient norm: 5.737: 95%|#########5| 594/625 [01:26<00:04, 6.91it/s]
reward: -2.2914, last reward: -0.0206, gradient norm: 0.485: 95%|#########5| 594/625 [01:26<00:04, 6.91it/s]
reward: -2.2914, last reward: -0.0206, gradient norm: 0.485: 95%|#########5| 595/625 [01:26<00:04, 6.88it/s]
reward: -2.0890, last reward: -0.0172, gradient norm: 0.3982: 95%|#########5| 595/625 [01:26<00:04, 6.88it/s]
reward: -2.0890, last reward: -0.0172, gradient norm: 0.3982: 95%|#########5| 596/625 [01:26<00:04, 6.83it/s]
reward: -2.0945, last reward: -0.0121, gradient norm: 0.4789: 95%|#########5| 596/625 [01:26<00:04, 6.83it/s]
reward: -2.0945, last reward: -0.0121, gradient norm: 0.4789: 96%|#########5| 597/625 [01:26<00:04, 6.81it/s]
reward: -2.3805, last reward: -0.0069, gradient norm: 0.4074: 96%|#########5| 597/625 [01:26<00:04, 6.81it/s]
reward: -2.3805, last reward: -0.0069, gradient norm: 0.4074: 96%|#########5| 598/625 [01:26<00:03, 6.82it/s]
reward: -2.3310, last reward: -0.0031, gradient norm: 0.5065: 96%|#########5| 598/625 [01:27<00:03, 6.82it/s]
reward: -2.3310, last reward: -0.0031, gradient norm: 0.5065: 96%|#########5| 599/625 [01:27<00:03, 6.83it/s]
reward: -2.6028, last reward: -0.0006, gradient norm: 0.6316: 96%|#########5| 599/625 [01:27<00:03, 6.83it/s]
reward: -2.6028, last reward: -0.0006, gradient norm: 0.6316: 96%|#########6| 600/625 [01:27<00:03, 6.88it/s]
reward: -2.6724, last reward: -0.0001, gradient norm: 0.6523: 96%|#########6| 600/625 [01:27<00:03, 6.88it/s]
reward: -2.6724, last reward: -0.0001, gradient norm: 0.6523: 96%|#########6| 601/625 [01:27<00:03, 6.85it/s]
reward: -2.2481, last reward: -0.0136, gradient norm: 0.4298: 96%|#########6| 601/625 [01:27<00:03, 6.85it/s]
reward: -2.2481, last reward: -0.0136, gradient norm: 0.4298: 96%|#########6| 602/625 [01:27<00:03, 6.85it/s]
reward: -2.3524, last reward: -0.0043, gradient norm: 0.2629: 96%|#########6| 602/625 [01:27<00:03, 6.85it/s]
reward: -2.3524, last reward: -0.0043, gradient norm: 0.2629: 96%|#########6| 603/625 [01:27<00:03, 6.83it/s]
reward: -2.2635, last reward: -0.0069, gradient norm: 0.7839: 96%|#########6| 603/625 [01:27<00:03, 6.83it/s]
reward: -2.2635, last reward: -0.0069, gradient norm: 0.7839: 97%|#########6| 604/625 [01:27<00:03, 6.81it/s]
reward: -2.6041, last reward: -0.8027, gradient norm: 11.7: 97%|#########6| 604/625 [01:28<00:03, 6.81it/s]
reward: -2.6041, last reward: -0.8027, gradient norm: 11.7: 97%|#########6| 605/625 [01:28<00:02, 6.83it/s]
reward: -4.4170, last reward: -3.4675, gradient norm: 60.04: 97%|#########6| 605/625 [01:28<00:02, 6.83it/s]
reward: -4.4170, last reward: -3.4675, gradient norm: 60.04: 97%|#########6| 606/625 [01:28<00:02, 6.85it/s]
reward: -4.3153, last reward: -2.9316, gradient norm: 53.11: 97%|#########6| 606/625 [01:28<00:02, 6.85it/s]
reward: -4.3153, last reward: -2.9316, gradient norm: 53.11: 97%|#########7| 607/625 [01:28<00:02, 6.85it/s]
reward: -3.0649, last reward: -0.9722, gradient norm: 30.84: 97%|#########7| 607/625 [01:28<00:02, 6.85it/s]
reward: -3.0649, last reward: -0.9722, gradient norm: 30.84: 97%|#########7| 608/625 [01:28<00:02, 6.84it/s]
reward: -2.7989, last reward: -0.0329, gradient norm: 1.261: 97%|#########7| 608/625 [01:28<00:02, 6.84it/s]
reward: -2.7989, last reward: -0.0329, gradient norm: 1.261: 97%|#########7| 609/625 [01:28<00:02, 6.86it/s]
reward: -2.1976, last reward: -0.6852, gradient norm: 20.33: 97%|#########7| 609/625 [01:28<00:02, 6.86it/s]
reward: -2.1976, last reward: -0.6852, gradient norm: 20.33: 98%|#########7| 610/625 [01:28<00:02, 6.84it/s]
reward: -2.4793, last reward: -0.1255, gradient norm: 14.69: 98%|#########7| 610/625 [01:28<00:02, 6.84it/s]
reward: -2.4793, last reward: -0.1255, gradient norm: 14.69: 98%|#########7| 611/625 [01:28<00:02, 6.85it/s]
reward: -2.4581, last reward: -0.0394, gradient norm: 2.429: 98%|#########7| 611/625 [01:29<00:02, 6.85it/s]
reward: -2.4581, last reward: -0.0394, gradient norm: 2.429: 98%|#########7| 612/625 [01:29<00:01, 6.86it/s]
reward: -2.2047, last reward: -0.0326, gradient norm: 1.147: 98%|#########7| 612/625 [01:29<00:01, 6.86it/s]
reward: -2.2047, last reward: -0.0326, gradient norm: 1.147: 98%|#########8| 613/625 [01:29<00:01, 6.90it/s]
reward: -1.8967, last reward: -0.0129, gradient norm: 0.8619: 98%|#########8| 613/625 [01:29<00:01, 6.90it/s]
reward: -1.8967, last reward: -0.0129, gradient norm: 0.8619: 98%|#########8| 614/625 [01:29<00:01, 6.88it/s]
reward: -2.5906, last reward: -0.0015, gradient norm: 0.6491: 98%|#########8| 614/625 [01:29<00:01, 6.88it/s]
reward: -2.5906, last reward: -0.0015, gradient norm: 0.6491: 98%|#########8| 615/625 [01:29<00:01, 6.90it/s]
reward: -1.6634, last reward: -0.0007, gradient norm: 0.4394: 98%|#########8| 615/625 [01:29<00:01, 6.90it/s]
reward: -1.6634, last reward: -0.0007, gradient norm: 0.4394: 99%|#########8| 616/625 [01:29<00:01, 6.87it/s]
reward: -2.0624, last reward: -0.0061, gradient norm: 0.5676: 99%|#########8| 616/625 [01:29<00:01, 6.87it/s]
reward: -2.0624, last reward: -0.0061, gradient norm: 0.5676: 99%|#########8| 617/625 [01:29<00:01, 6.84it/s]
reward: -2.3259, last reward: -0.0131, gradient norm: 0.7733: 99%|#########8| 617/625 [01:29<00:01, 6.84it/s]
reward: -2.3259, last reward: -0.0131, gradient norm: 0.7733: 99%|#########8| 618/625 [01:29<00:01, 6.84it/s]
reward: -1.7515, last reward: -0.0189, gradient norm: 0.5575: 99%|#########8| 618/625 [01:30<00:01, 6.84it/s]
reward: -1.7515, last reward: -0.0189, gradient norm: 0.5575: 99%|#########9| 619/625 [01:30<00:00, 6.84it/s]
reward: -1.9313, last reward: -0.0207, gradient norm: 0.6286: 99%|#########9| 619/625 [01:30<00:00, 6.84it/s]
reward: -1.9313, last reward: -0.0207, gradient norm: 0.6286: 99%|#########9| 620/625 [01:30<00:00, 6.85it/s]
reward: -2.4325, last reward: -0.0171, gradient norm: 0.7832: 99%|#########9| 620/625 [01:30<00:00, 6.85it/s]
reward: -2.4325, last reward: -0.0171, gradient norm: 0.7832: 99%|#########9| 621/625 [01:30<00:00, 6.86it/s]
reward: -2.1134, last reward: -0.0144, gradient norm: 1.96: 99%|#########9| 621/625 [01:30<00:00, 6.86it/s]
reward: -2.1134, last reward: -0.0144, gradient norm: 1.96: 100%|#########9| 622/625 [01:30<00:00, 6.84it/s]
reward: -2.4572, last reward: -0.0500, gradient norm: 0.5838: 100%|#########9| 622/625 [01:30<00:00, 6.84it/s]
reward: -2.4572, last reward: -0.0500, gradient norm: 0.5838: 100%|#########9| 623/625 [01:30<00:00, 6.82it/s]
reward: -2.3818, last reward: -0.0019, gradient norm: 0.8623: 100%|#########9| 623/625 [01:30<00:00, 6.82it/s]
reward: -2.3818, last reward: -0.0019, gradient norm: 0.8623: 100%|#########9| 624/625 [01:30<00:00, 6.85it/s]
reward: -2.1253, last reward: -0.0001, gradient norm: 0.6622: 100%|#########9| 624/625 [01:30<00:00, 6.85it/s]
reward: -2.1253, last reward: -0.0001, gradient norm: 0.6622: 100%|##########| 625/625 [01:30<00:00, 6.83it/s]
reward: -2.1253, last reward: -0.0001, gradient norm: 0.6622: 100%|##########| 625/625 [01:30<00:00, 6.87it/s]
结论¶
在本教程中，我们学习了如何从头开始编写无状态环境。我们涉及了以下主题：
编写环境时需要处理的四个基本组件（
step，reset，播种和构建规范）。我们看到了这些方法和类如何与TensorDict类交互；如何使用
check_env_specs()测试环境是否编码正确；如何在无状态环境的上下文中追加转换以及如何编写自定义转换；
如何在完全可微的模拟器上训练策略。
脚本总运行时间：（1 分 31.197 秒）
