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')

註冊來自具有 lives 方法的 Gym 環境的生命結束訊號。

由 DeepMind 為 DQN 及同類產品提出。它有助於價值估計。

引數:

• eol_key (NestedKey, optional) – 應該寫入生命結束訊號的鍵。預設為 "end-of-life"。

• done_key (NestedKey, optional) – 父環境 done_spec 中的一個“done”鍵，可以從中檢索 done 值。此鍵必須是唯一的，並且其形狀必須與生命結束條目匹配。預設為 "done"。

• eol_attribute (str, optional) – gym 環境中“lives”的位置。預設為 "unwrapped.ale.lives"。支援的屬性型別是整數/類陣列物件或返回這些值的可呼叫物件。

注意

此轉換應與具有 env.unwrapped.ale.lives 的 gym 環境一起使用。

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)

此轉換的典型用法是在損失模組中用“生命結束”替換“done”狀態。生命結束訊號未在 done_spec 中註冊，因為它不應該指示環境重置。

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

讀取輸入 tensordict，並對選定的鍵應用轉換。

預設情況下，此方法

• 直接呼叫 _apply_transform()。

• 不呼叫 _step() 或 _call()。

此方法不會在任何時候在 env.step 中呼叫。但是，它會在 sample() 中呼叫。

注意

forward 也可以使用 dispatch 將引數名稱轉換為鍵，並使用常規關鍵字引數。

示例

>>> class TransformThatMeasuresBytes(Transform):
...     '''Measures the number of bytes in the tensordict, and writes it under `"bytes"`.'''
...     def __init__(self):
...         super().__init__(in_keys=[], out_keys=["bytes"])
...
...     def forward(self, tensordict: TensorDictBase) -> TensorDictBase:
...         bytes_in_td = tensordict.bytes()
...         tensordict["bytes"] = bytes
...         return tensordict
>>> t = TransformThatMeasuresBytes()
>>> env = env.append_transform(t) # works within envs
>>> t(TensorDict(a=0))  # Works offline too.

register_keys(loss_or_advantage: torchrl.objectives.common.LossModule)

在損失的適當位置註冊生命結束鍵。

引數:

loss_or_advantage (torchrl.objectives.LossModule 或 torchrl.objectives.value.ValueEstimatorBase) – 用於指示生命結束鍵是什麼的模組。

transform_observation_spec(observation_spec)

轉換觀察規範，使結果規範與轉換對映匹配。

引數:

observation_spec (TensorSpec) – 轉換前的規範

返回:

轉換後的預期規範