MultiStepActorWrapper

class torchrl.modules.tensordict_module.MultiStepActorWrapper(*args, **kwargs)

多动作 actor 的包装器。

此类使宏能够在环境中执行。actor 的动作条目必须具有额外的时间维度才能被消耗。它必须放置在输入 tensordict 的最后一个维度旁边（即在 tensordict.ndim）。

如果未使用简单的启发式方法（任何以 "action" 字符串结尾的嵌套键）提供，则会自动从 actor 检索动作条目键。

输入 tensordict 中还必须存在 "is_init" 条目，以跟踪何时以及为何应中断当前集合，因为遇到了“完成”状态。与 action_keys 不同，此键必须是唯一的。

参数:

• actor (TensorDictModuleBase) – 一个 actor。

• n_steps (int) – actor 一次输出的动作数（前瞻窗口）。

关键字参数:

• action_keys (list of NestedKeys, optional) – 来自环境的动作键。可以从 env.action_keys 检索。默认为 actor 的所有以 "action" 字符串结尾的 out_keys。

• init_key (NestedKey, optional) – 指示环境何时经历重置的条目的键。默认为 "is_init"，它是 InitTracker 转换的 out_key。

示例

>>> import torch.nn
>>> from torchrl.modules.tensordict_module.actors import MultiStepActorWrapper, Actor
>>> from torchrl.envs import CatFrames, GymEnv, TransformedEnv, SerialEnv, InitTracker, Compose
>>> from tensordict.nn import TensorDictSequential as Seq, TensorDictModule as Mod
>>>
>>> time_steps = 6
>>> n_obs = 4
>>> n_action = 2
>>> batch = 5
>>>
>>> # Transforms a CatFrames in a stack of frames
>>> def reshape_cat(data: torch.Tensor):
...     return data.unflatten(-1, (time_steps, n_obs))
>>> # an actor that reads `time_steps` frames and outputs one action per frame
>>> # (actions are conditioned on the observation of `time_steps` in the past)
>>> actor_base = Seq(
...     Mod(reshape_cat, in_keys=["obs_cat"], out_keys=["obs_cat_reshape"]),
...     Mod(torch.nn.Linear(n_obs, n_action), in_keys=["obs_cat_reshape"], out_keys=["action"])
... )
>>> # Wrap the actor to dispatch the actions
>>> actor = MultiStepActorWrapper(actor_base, n_steps=time_steps)
>>>
>>> env = TransformedEnv(
...     SerialEnv(batch, lambda: GymEnv("CartPole-v1")),
...     Compose(
...         InitTracker(),
...         CatFrames(N=time_steps, in_keys=["observation"], out_keys=["obs_cat"], dim=-1)
...     )
... )
>>>
>>> print(env.rollout(100, policy=actor, break_when_any_done=False))
TensorDict(
    fields={
        action: Tensor(shape=torch.Size([5, 100, 2]), device=cpu, dtype=torch.float32, is_shared=False),
        action_orig: Tensor(shape=torch.Size([5, 100, 6, 2]), device=cpu, dtype=torch.float32, is_shared=False),
        counter: Tensor(shape=torch.Size([5, 100, 1]), device=cpu, dtype=torch.int32, is_shared=False),
        done: Tensor(shape=torch.Size([5, 100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        is_init: Tensor(shape=torch.Size([5, 100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        next: TensorDict(
            fields={
                done: Tensor(shape=torch.Size([5, 100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                is_init: Tensor(shape=torch.Size([5, 100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                obs_cat: Tensor(shape=torch.Size([5, 100, 24]), device=cpu, dtype=torch.float32, is_shared=False),
                observation: Tensor(shape=torch.Size([5, 100, 4]), device=cpu, dtype=torch.float32, is_shared=False),
                reward: Tensor(shape=torch.Size([5, 100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
                terminated: Tensor(shape=torch.Size([5, 100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                truncated: Tensor(shape=torch.Size([5, 100, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
            batch_size=torch.Size([5, 100]),
            device=cpu,
            is_shared=False),
        obs_cat: Tensor(shape=torch.Size([5, 100, 24]), device=cpu, dtype=torch.float32, is_shared=False),
        observation: Tensor(shape=torch.Size([5, 100, 4]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([5, 100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([5, 100, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
    batch_size=torch.Size([5, 100]),
    device=cpu,
    is_shared=False)

forward(tensordict: TensorDictBase) → TensorDictBase

定义每次调用时执行的计算。

应由所有子类重写。

注意

虽然前向传递的配方需要在该函数中定义，但应该在之后调用 Module 实例而不是此函数，因为前者负责运行注册的钩子，而后者会静默地忽略它们。

property init_key: NestedKey

批次中给定元素的初始步骤的指示符。