EndOfLifeTransform

class torchrl.envs.transforms.EndOfLifeTransform(eol_key: NestedKey = 'end-of-life', lives_key: NestedKey = 'lives', done_key: NestedKey = 'done', eol_attribute='unwrapped.ale.lives')

将来自具有 lives 方法的 Gym 环境的寿命结束信号注册到一个 lives 方法中。

由 DeepMind 为 DQN 等提出。它有助于价值估计。

参数：:

• eol_key (NestedKey, 可选) – 应写入寿命结束信号的键。默认为 "end-of-life"。

• done_key (NestedKey, 可选) – 父环境 done_spec 中的“done”键，可以在其中检索 done 值。此键必须是唯一的，其形状必须与寿命结束项的形状匹配。默认为 "done"。

• eol_attribute (str, 可选) – Gym 环境中“lives”的位置。默认为 "unwrapped.ale.lives"。支持的属性类型是整数/类似数组的对象或返回这些值的 callable。

注意

此转换应与具有 env.unwrapped.ale.lives 的 Gym 环境一起使用。

示例

>>> from torchrl.envs.libs.gym import GymEnv
>>> from torchrl.envs.transforms.transforms import TransformedEnv
>>> env = GymEnv("ALE/Breakout-v5")
>>> env.rollout(100)
TensorDict(
    fields={
        action: Tensor(shape=torch.Size([100, 4]), device=cpu, dtype=torch.int64, is_shared=False),
        done: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        next: TensorDict(
            fields={
                done: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                pixels: Tensor(shape=torch.Size([100, 210, 160, 3]), device=cpu, dtype=torch.uint8, is_shared=False),
                reward: 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),
                truncated: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
            batch_size=torch.Size([100]),
            device=cpu,
            is_shared=False),
        pixels: Tensor(shape=torch.Size([100, 210, 160, 3]), device=cpu, dtype=torch.uint8, is_shared=False),
        terminated: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
    batch_size=torch.Size([100]),
    device=cpu,
    is_shared=False)
>>> eol_transform = EndOfLifeTransform()
>>> env = TransformedEnv(env, eol_transform)
>>> env.rollout(100)
TensorDict(
    fields={
        action: Tensor(shape=torch.Size([100, 4]), device=cpu, dtype=torch.int64, is_shared=False),
        done: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        eol: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        lives: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.int64, is_shared=False),
        next: TensorDict(
            fields={
                done: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                end-of-life: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                lives: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.int64, is_shared=False),
                pixels: Tensor(shape=torch.Size([100, 210, 160, 3]), device=cpu, dtype=torch.uint8, is_shared=False),
                reward: 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),
                truncated: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
            batch_size=torch.Size([100]),
            device=cpu,
            is_shared=False),
        pixels: Tensor(shape=torch.Size([100, 210, 160, 3]), device=cpu, dtype=torch.uint8, is_shared=False),
        terminated: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
    batch_size=torch.Size([100]),
    device=cpu,
    is_shared=False)

此转换的典型用法是将损失模块中的“done”状态替换为“寿命结束”。寿命结束信号没有注册到 done_spec 中，因为它不应该指示环境重置。

示例

>>> from torchrl.objectives import DQNLoss
>>> module = torch.nn.Identity() # used as a placeholder
>>> loss = DQNLoss(module, action_space="categorical")
>>> loss.set_keys(done="end-of-life", terminated="end-of-life")
>>> # equivalently
>>> eol_transform.register_keys(loss)

forward(tensordict: TensorDictBase) → TensorDictBase

读取输入 tensordict，并针对选定的键应用转换。

register_keys(loss_or_advantage: LossModule)

在损失中的适当位置注册寿命结束键。

参数：:

loss_or_advantage (torchrl.objectives.LossModule 或 torchrl.objectives.value.ValueEstimatorBase) – 指示寿命结束键的模块。

transform_observation_spec(observation_spec)

转换观测规范，使得到的规范与转换映射匹配。

参数：:

observation_spec (TensorSpec) – 转换前的规范

返回值：:

转换后的预期规范