AtariDQNExperienceReplay

class torchrl.data.datasets.AtariDQNExperienceReplay(dataset_id: str, batch_size: int | None = None, *, root: str | Path | None = None, download: bool | str = True, sampler=None, writer=None, transform: 'Transform' | None = None, num_procs: int = 0, num_slices: int | None = None, slice_len: int | None = None, strict_len: bool = True, replacement: bool = True, mp_start_method: str = 'fork', **kwargs)

Atari DQN 经验回放类。

Atari DQN 数据集 (https://offline-rl.github.io/) 是对 Atari 2600 游戏的 5 次 DQN 训练迭代的集合，总共包含 2 亿帧。子采样率（帧跳跃）等于 4，这意味着每个游戏数据集总共有 5000 万步。

数据格式遵循 TED 约定。由于数据集相当庞大，因此数据格式化是在采样时在线完成的。

为了使训练更加模块化，我们将数据集拆分为每个 Atari 游戏并分别存储每次训练轮次。因此，每个数据集都表示为长度为 5000 万个元素的存储。在底层，此数据集被拆分为 50 个长度为 100 万的内存映射张量字典。

参数：

• dataset_id (str) – 要下载的数据集。必须是 AtariDQNExperienceReplay.available_datasets 的一部分。

• batch_size (int) – 采样期间使用的批大小。如有必要，可以通过 data.sample(batch_size) 覆盖。

关键字参数：

• root (Path 或 str, 可选) – AtariDQN 数据集的根目录。实际的数据集内存映射文件将保存在 <root>/<dataset_id> 下。如果未提供，则默认为 ``~/.cache/torchrl/atari`。

• num_procs (int, 可选) – 用于预处理的进程数。在数据已下载时无效。默认为 0（不使用多处理）。

• download (bool 或 str, 可选) – 如果未找到数据集，是否应下载。默认为 True。下载也可以作为 "force" 传递，在这种情况下，下载的数据将被覆盖。

• sampler (Sampler, 可选) – 要使用的采样器。如果未提供，则将使用默认的 RandomSampler()。

• writer (Writer, 可选) – 要使用的写入器。如果未提供，则将使用默认的 ImmutableDatasetWriter。

• collate_fn (callable, 可选) – 将样本列表合并以形成张量/输出的小批量。在从映射式数据集使用批量加载时使用。

• pin_memory (bool) – 是否应在 rb 样本上调用 pin_memory()。

• prefetch (int, 可选) – 使用多线程预取的下一个批次的数目。

• transform (Transform, 可选) – 调用 sample() 时要执行的转换。要链接转换，请使用 Compose 类。

• num_slices (int, 可选) – 要采样的切片数量。批大小必须大于或等于num_slices参数。与slice_len互斥。默认为None（不进行切片采样）。sampler参数将覆盖此值。

• slice_len (int, 可选) – 要采样的切片的长度。批大小必须大于或等于slice_len参数，并且可以被其整除。与num_slices互斥。默认为None（不进行切片采样）。sampler参数将覆盖此值。

• strict_length (bool, 可选) – 如果为False，则允许长度短于slice_len（或batch_size // num_slices）的轨迹出现在批次中。请注意，这可能导致有效batch_size短于请求的批大小！可以使用torchrl.collectors.split_trajectories()分割轨迹。默认为True。sampler参数将覆盖此值。

• replacement (bool, 可选) – 如果为False，则采样将不进行替换。 sampler参数将覆盖此值。

• mp_start_method (str, 可选) – 多进程下载的启动方法。默认为"fork"。

变量：

• available_datasets – 可用数据集列表，格式为<game_name>/<run>。例如：“Pong/5”，“Krull/2”，…

• dataset_id (str) – 数据集的名称。

• episodes (torch.Tensor) – 一个1D张量，指示1M帧中的每个帧属于哪个运行。与SliceSampler一起使用，可以廉价地对片段进行采样。

示例

>>> from torchrl.data.datasets import AtariDQNExperienceReplay
>>> dataset = AtariDQNExperienceReplay("Pong/5", batch_size=128)
>>> for data in dataset:
...     print(data)
...     break
TensorDict(
    fields={
        action: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.int32, is_shared=False),
        done: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.uint8, is_shared=False),
        index: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.int64, is_shared=False),
        metadata: NonTensorData(
            data={'invalid_range': MemoryMappedTensor([999998, 999999,      0,      1,      2]), 'add_count': MemoryMappedTensor(999999), 'dataset_id': 'Pong/5'}},
            batch_size=torch.Size([128]),
            device=None,
            is_shared=False),
        next: TensorDict(
            fields={
                done: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.uint8, is_shared=False),
                observation: Tensor(shape=torch.Size([128, 84, 84]), device=cpu, dtype=torch.uint8, is_shared=False),
                reward: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.float32, is_shared=False),
                terminated: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.uint8, is_shared=False),
                truncated: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.uint8, is_shared=False)},
            batch_size=torch.Size([128]),
            device=None,
            is_shared=False),
        observation: Tensor(shape=torch.Size([128, 84, 84]), device=cpu, dtype=torch.uint8, is_shared=False),
        terminated: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.uint8, is_shared=False),
        truncated: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.uint8, is_shared=False)},
    batch_size=torch.Size([128]),
    device=None,
    is_shared=False)

警告

Atari-DQN在终止信号后不提供下一个观察结果。换句话说，当("next", "done")为True时，无法获取("next", "observation")状态。此值填充为0，但在实践中不应使用。如果使用TorchRL的值估计器（ValueEstimator），则这应该不是问题。

注意

由于用于片段采样的采样器的构建略显复杂，因此我们使用户可以轻松地将SliceSampler的参数直接传递给AtariDQNExperienceReplay数据集：任何num_slices或slice_len参数都将使采样器成为SliceSampler的实例。strict_length也可以传递。

>>> from torchrl.data.datasets import AtariDQNExperienceReplay
>>> from torchrl.data.replay_buffers import SliceSampler
>>> dataset = AtariDQNExperienceReplay("Pong/5", batch_size=128, slice_len=64)
>>> for data in dataset:
...     print(data)
...     print(data.get("index"))  # indices are in 4 groups of consecutive values
...     break
TensorDict(
    fields={
        action: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.int32, is_shared=False),
        done: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.uint8, is_shared=False),
        index: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.int64, is_shared=False),
        metadata: NonTensorData(
            data={'invalid_range': MemoryMappedTensor([999998, 999999,      0,      1,      2]), 'add_count': MemoryMappedTensor(999999), 'dataset_id': 'Pong/5'}},
            batch_size=torch.Size([128]),
            device=None,
            is_shared=False),
        next: TensorDict(
            fields={
                done: Tensor(shape=torch.Size([128, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                observation: Tensor(shape=torch.Size([128, 84, 84]), device=cpu, dtype=torch.uint8, is_shared=False),
                reward: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.float32, is_shared=False),
                terminated: Tensor(shape=torch.Size([128, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                truncated: Tensor(shape=torch.Size([128, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
            batch_size=torch.Size([128]),
            device=None,
            is_shared=False),
        observation: Tensor(shape=torch.Size([128, 84, 84]), device=cpu, dtype=torch.uint8, is_shared=False),
        terminated: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.uint8, is_shared=False),
        truncated: Tensor(shape=torch.Size([128]), device=cpu, dtype=torch.uint8, is_shared=False)},
    batch_size=torch.Size([128]),
    device=None,
    is_shared=False)
tensor([2657628, 2657629, 2657630, 2657631, 2657632, 2657633, 2657634, 2657635,
        2657636, 2657637, 2657638, 2657639, 2657640, 2657641, 2657642, 2657643,
        2657644, 2657645, 2657646, 2657647, 2657648, 2657649, 2657650, 2657651,
        2657652, 2657653, 2657654, 2657655, 2657656, 2657657, 2657658, 2657659,
        2657660, 2657661, 2657662, 2657663, 2657664, 2657665, 2657666, 2657667,
        2657668, 2657669, 2657670, 2657671, 2657672, 2657673, 2657674, 2657675,
        2657676, 2657677, 2657678, 2657679, 2657680, 2657681, 2657682, 2657683,
        2657684, 2657685, 2657686, 2657687, 2657688, 2657689, 2657690, 2657691,
        1995687, 1995688, 1995689, 1995690, 1995691, 1995692, 1995693, 1995694,
        1995695, 1995696, 1995697, 1995698, 1995699, 1995700, 1995701, 1995702,
        1995703, 1995704, 1995705, 1995706, 1995707, 1995708, 1995709, 1995710,
        1995711, 1995712, 1995713, 1995714, 1995715, 1995716, 1995717, 1995718,
        1995719, 1995720, 1995721, 1995722, 1995723, 1995724, 1995725, 1995726,
        1995727, 1995728, 1995729, 1995730, 1995731, 1995732, 1995733, 1995734,
        1995735, 1995736, 1995737, 1995738, 1995739, 1995740, 1995741, 1995742,
        1995743, 1995744, 1995745, 1995746, 1995747, 1995748, 1995749, 1995750])

注意

与往常一样，数据集应使用ReplayBufferEnsemble组合

>>> from torchrl.data.datasets import AtariDQNExperienceReplay
>>> from torchrl.data.replay_buffers import ReplayBufferEnsemble
>>> # we change this parameter for quick experimentation, in practice it should be left untouched
>>> AtariDQNExperienceReplay._max_runs = 2
>>> dataset_asterix = AtariDQNExperienceReplay("Asterix/5", batch_size=128, slice_len=64, num_procs=4)
>>> dataset_pong = AtariDQNExperienceReplay("Pong/5", batch_size=128, slice_len=64, num_procs=4)
>>> dataset = ReplayBufferEnsemble(dataset_pong, dataset_asterix, batch_size=128, sample_from_all=True)
>>> sample = dataset.sample()
>>> print("first sample, Asterix", sample[0])
first sample, Asterix TensorDict(
    fields={
        action: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.int32, is_shared=False),
        done: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.uint8, is_shared=False),
        index: TensorDict(
            fields={
                buffer_ids: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.int64, is_shared=False),
                index: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.int64, is_shared=False)},
            batch_size=torch.Size([64]),
            device=None,
            is_shared=False),
        metadata: NonTensorData(
            data={'invalid_range': MemoryMappedTensor([999998, 999999,      0,      1,      2]), 'add_count': MemoryMappedTensor(999999), 'dataset_id': 'Pong/5'},
            batch_size=torch.Size([64]),
            device=None,
            is_shared=False),
        next: TensorDict(
            fields={
                done: Tensor(shape=torch.Size([64, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                observation: Tensor(shape=torch.Size([64, 84, 84]), device=cpu, dtype=torch.uint8, is_shared=False),
                reward: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.float32, is_shared=False),
                terminated: Tensor(shape=torch.Size([64, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                truncated: Tensor(shape=torch.Size([64, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
            batch_size=torch.Size([64]),
            device=None,
            is_shared=False),
        observation: Tensor(shape=torch.Size([64, 84, 84]), device=cpu, dtype=torch.uint8, is_shared=False),
        terminated: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.uint8, is_shared=False),
        truncated: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.uint8, is_shared=False)},
    batch_size=torch.Size([64]),
    device=None,
    is_shared=False)
>>> print("second sample, Pong", sample[1])
second sample, Pong TensorDict(
    fields={
        action: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.int32, is_shared=False),
        done: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.uint8, is_shared=False),
        index: TensorDict(
            fields={
                buffer_ids: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.int64, is_shared=False),
                index: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.int64, is_shared=False)},
            batch_size=torch.Size([64]),
            device=None,
            is_shared=False),
        metadata: NonTensorData(
            data={'invalid_range': MemoryMappedTensor([999998, 999999,      0,      1,      2]), 'add_count': MemoryMappedTensor(999999), 'dataset_id': 'Asterix/5'},
            batch_size=torch.Size([64]),
            device=None,
            is_shared=False),
        next: TensorDict(
            fields={
                done: Tensor(shape=torch.Size([64, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                observation: Tensor(shape=torch.Size([64, 84, 84]), device=cpu, dtype=torch.uint8, is_shared=False),
                reward: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.float32, is_shared=False),
                terminated: Tensor(shape=torch.Size([64, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                truncated: Tensor(shape=torch.Size([64, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
            batch_size=torch.Size([64]),
            device=None,
            is_shared=False),
        observation: Tensor(shape=torch.Size([64, 84, 84]), device=cpu, dtype=torch.uint8, is_shared=False),
        terminated: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.uint8, is_shared=False),
        truncated: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.uint8, is_shared=False)},
    batch_size=torch.Size([64]),
    device=None,
    is_shared=False)
>>> print("Aggregate (metadata hidden)", sample)
Aggregate (metadata hidden) LazyStackedTensorDict(
    fields={
        action: Tensor(shape=torch.Size([2, 64]), device=cpu, dtype=torch.int32, is_shared=False),
        done: Tensor(shape=torch.Size([2, 64]), device=cpu, dtype=torch.uint8, is_shared=False),
        index: LazyStackedTensorDict(
            fields={
                buffer_ids: Tensor(shape=torch.Size([2, 64]), device=cpu, dtype=torch.int64, is_shared=False),
                index: Tensor(shape=torch.Size([2, 64]), device=cpu, dtype=torch.int64, is_shared=False)},
            exclusive_fields={
            },
            batch_size=torch.Size([2, 64]),
            device=None,
            is_shared=False,
            stack_dim=0),
        metadata: LazyStackedTensorDict(
            fields={
            },
            exclusive_fields={
            },
            batch_size=torch.Size([2, 64]),
            device=None,
            is_shared=False,
            stack_dim=0),
        next: LazyStackedTensorDict(
            fields={
                done: Tensor(shape=torch.Size([2, 64, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                observation: Tensor(shape=torch.Size([2, 64, 84, 84]), device=cpu, dtype=torch.uint8, is_shared=False),
                reward: Tensor(shape=torch.Size([2, 64]), device=cpu, dtype=torch.float32, is_shared=False),
                terminated: Tensor(shape=torch.Size([2, 64, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                truncated: Tensor(shape=torch.Size([2, 64, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
            exclusive_fields={
            },
            batch_size=torch.Size([2, 64]),
            device=None,
            is_shared=False,
            stack_dim=0),
        observation: Tensor(shape=torch.Size([2, 64, 84, 84]), device=cpu, dtype=torch.uint8, is_shared=False),
        terminated: Tensor(shape=torch.Size([2, 64]), device=cpu, dtype=torch.uint8, is_shared=False),
        truncated: Tensor(shape=torch.Size([2, 64]), device=cpu, dtype=torch.uint8, is_shared=False)},
    exclusive_fields={
    },
    batch_size=torch.Size([2, 64]),
    device=None,
    is_shared=False,
    stack_dim=0)

add(data: TensorDictBase) → int

将单个元素添加到回放缓冲区。

参数：

data (Any) – 要添加到回放缓冲区的数据

返回值：

数据在回放缓冲区中的索引。

append_transform(transform: Transform, *, invert: bool = False) → ReplayBuffer

在末尾追加转换。

当调用sample时，转换将按顺序应用。

参数：

transform (Transform) – 要追加的转换

关键字参数：

invert (bool, 可选) – 如果为True，则转换将被反转（正向调用将在写入期间调用，反向调用将在读取期间调用）。默认为False。

示例

>>> rb = ReplayBuffer(storage=LazyMemmapStorage(10), batch_size=4)
>>> data = TensorDict({"a": torch.zeros(10)}, [10])
>>> def t(data):
...     data += 1
...     return data
>>> rb.append_transform(t, invert=True)
>>> rb.extend(data)
>>> assert (data == 1).all()

抽象 属性 data_path: Path

数据集的路径，包括分割。

抽象 属性 data_path_root: Path

数据集根目录的路径。

delete()

从磁盘删除数据集存储。

dump(*args, **kwargs)

dumps()的别名。

dumps(path)

将回放缓冲区保存到指定路径的磁盘上。

参数：

path (Path 或 str) – 保存回放缓冲区的路径。

示例

>>> import tempfile
>>> import tqdm
>>> from torchrl.data import LazyMemmapStorage, TensorDictReplayBuffer
>>> from torchrl.data.replay_buffers.samplers import PrioritizedSampler, RandomSampler
>>> import torch
>>> from tensordict import TensorDict
>>> # Build and populate the replay buffer
>>> S = 1_000_000
>>> sampler = PrioritizedSampler(S, 1.1, 1.0)
>>> # sampler = RandomSampler()
>>> storage = LazyMemmapStorage(S)
>>> rb = TensorDictReplayBuffer(storage=storage, sampler=sampler)
>>>
>>> for _ in tqdm.tqdm(range(100)):
...     td = TensorDict({"obs": torch.randn(100, 3, 4), "next": {"obs": torch.randn(100, 3, 4)}, "td_error": torch.rand(100)}, [100])
...     rb.extend(td)
...     sample = rb.sample(32)
...     rb.update_tensordict_priority(sample)
>>> # save and load the buffer
>>> with tempfile.TemporaryDirectory() as tmpdir:
...     rb.dumps(tmpdir)
...
...     sampler = PrioritizedSampler(S, 1.1, 1.0)
...     # sampler = RandomSampler()
...     storage = LazyMemmapStorage(S)
...     rb_load = TensorDictReplayBuffer(storage=storage, sampler=sampler)
...     rb_load.loads(tmpdir)
...     assert len(rb) == len(rb_load)

empty()

清空回放缓冲区并将游标重置为0。

extend(tensordicts: TensorDictBase) → Tensor

使用可迭代对象中包含的一个或多个元素扩展回放缓冲区。

如果存在，将调用逆转换。

参数：

data (iterable) – 要添加到回放缓冲区的数据集合。

返回值：

添加到回放缓冲区的数据的索引。

警告

extend()在处理值列表时可能具有模棱两可的签名，这些值应解释为PyTree（在这种情况下，列表中的所有元素都将被放入存储中存储的PyTree中的切片）或要逐个添加的值列表。为了解决这个问题，TorchRL在列表和元组之间做出了明确的区别：元组将被视为PyTree，列表（在根级别）将被解释为要逐个添加到缓冲区的值的堆栈。对于ListStorage实例，只能提供未绑定元素（无PyTree）。

insert_transform(index: int, transform: Transform, *, invert: bool = False) → ReplayBuffer

插入转换。

当调用sample时，转换将按顺序执行。

参数：

• index (int) – 插入转换的位置。

• transform (Transform) – 要追加的转换

关键字参数：

invert (bool, 可选) – 如果为True，则转换将被反转（正向调用将在写入期间调用，反向调用将在读取期间调用）。默认为False。

load(*args, **kwargs)

loads() 的别名。

loads(path)

加载给定路径下的回放缓冲区状态。

缓冲区应具有匹配的组件，并使用 dumps() 保存。

参数：

path (Path 或 str) – 保存回放缓冲区的路径。

有关更多信息，请参阅 dumps()。

preprocess(fn: Callable[[TensorDictBase], TensorDictBase], dim: int = 0, num_workers: int | None = None, *, chunksize: int | None = None, num_chunks: int | None = None, pool: mp.Pool | None = None, generator: torch.Generator | None = None, max_tasks_per_child: int | None = None, worker_threads: int = 1, index_with_generator: bool = False, pbar: bool = False, mp_start_method: str | None = None, dest: str | Path, num_frames: int | None = None)

预处理数据集并返回包含格式化数据的新的存储。

数据转换必须是单一的（作用于数据集的单个样本）。

参数和关键字参数被转发到 map()。

随后可以使用 delete() 删除数据集。

关键字参数：

• dest (path 或 等价物) – 新数据集所在位置的路径。

• num_frames (int, 可选) – 如果提供，则仅转换前 num_frames。这在开始时调试转换很有用。

返回：一个新的存储，可在 ReplayBuffer 实例中使用。

示例

>>> from torchrl.data.datasets import MinariExperienceReplay
>>>
>>> data = MinariExperienceReplay(
...     list(MinariExperienceReplay.available_datasets)[0],
...     batch_size=32
...     )
>>> print(data)
MinariExperienceReplay(
    storages=TensorStorage(TensorDict(
        fields={
            action: MemoryMappedTensor(shape=torch.Size([1000000, 8]), device=cpu, dtype=torch.float32, is_shared=True),
            episode: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.int64, is_shared=True),
            info: TensorDict(
                fields={
                    distance_from_origin: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                    forward_reward: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                    goal: MemoryMappedTensor(shape=torch.Size([1000000, 2]), device=cpu, dtype=torch.float64, is_shared=True),
                    qpos: MemoryMappedTensor(shape=torch.Size([1000000, 15]), device=cpu, dtype=torch.float64, is_shared=True),
                    qvel: MemoryMappedTensor(shape=torch.Size([1000000, 14]), device=cpu, dtype=torch.float64, is_shared=True),
                    reward_ctrl: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                    reward_forward: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                    reward_survive: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                    success: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.bool, is_shared=True),
                    x_position: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                    x_velocity: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                    y_position: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                    y_velocity: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True)},
                batch_size=torch.Size([1000000]),
                device=cpu,
                is_shared=False),
            next: TensorDict(
                fields={
                    done: MemoryMappedTensor(shape=torch.Size([1000000, 1]), device=cpu, dtype=torch.bool, is_shared=True),
                    info: TensorDict(
                        fields={
                            distance_from_origin: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                            forward_reward: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                            goal: MemoryMappedTensor(shape=torch.Size([1000000, 2]), device=cpu, dtype=torch.float64, is_shared=True),
                            qpos: MemoryMappedTensor(shape=torch.Size([1000000, 15]), device=cpu, dtype=torch.float64, is_shared=True),
                            qvel: MemoryMappedTensor(shape=torch.Size([1000000, 14]), device=cpu, dtype=torch.float64, is_shared=True),
                            reward_ctrl: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                            reward_forward: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                            reward_survive: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                            success: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.bool, is_shared=True),
                            x_position: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                            x_velocity: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                            y_position: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True),
                            y_velocity: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.float64, is_shared=True)},
                        batch_size=torch.Size([1000000]),
                        device=cpu,
                        is_shared=False),
                    observation: TensorDict(
                        fields={
                            achieved_goal: MemoryMappedTensor(shape=torch.Size([1000000, 2]), device=cpu, dtype=torch.float64, is_shared=True),
                            desired_goal: MemoryMappedTensor(shape=torch.Size([1000000, 2]), device=cpu, dtype=torch.float64, is_shared=True),
                            observation: MemoryMappedTensor(shape=torch.Size([1000000, 27]), device=cpu, dtype=torch.float64, is_shared=True)},
                        batch_size=torch.Size([1000000]),
                        device=cpu,
                        is_shared=False),
                    reward: MemoryMappedTensor(shape=torch.Size([1000000, 1]), device=cpu, dtype=torch.float64, is_shared=True),
                    terminated: MemoryMappedTensor(shape=torch.Size([1000000, 1]), device=cpu, dtype=torch.bool, is_shared=True),
                    truncated: MemoryMappedTensor(shape=torch.Size([1000000, 1]), device=cpu, dtype=torch.bool, is_shared=True)},
                batch_size=torch.Size([1000000]),
                device=cpu,
                is_shared=False),
            observation: TensorDict(
                fields={
                    achieved_goal: MemoryMappedTensor(shape=torch.Size([1000000, 2]), device=cpu, dtype=torch.float64, is_shared=True),
                    desired_goal: MemoryMappedTensor(shape=torch.Size([1000000, 2]), device=cpu, dtype=torch.float64, is_shared=True),
                    observation: MemoryMappedTensor(shape=torch.Size([1000000, 27]), device=cpu, dtype=torch.float64, is_shared=True)},
                batch_size=torch.Size([1000000]),
                device=cpu,
                is_shared=False)},
        batch_size=torch.Size([1000000]),
        device=cpu,
        is_shared=False)),
    samplers=RandomSampler,
    writers=ImmutableDatasetWriter(),
batch_size=32,
transform=Compose(
),
collate_fn=<function _collate_id at 0x120e21dc0>)
>>> from torchrl.envs import CatTensors, Compose
>>> from tempfile import TemporaryDirectory
>>>
>>> cat_tensors = CatTensors(
...     in_keys=[("observation", "observation"), ("observation", "achieved_goal"),
...              ("observation", "desired_goal")],
...     out_key="obs"
...     )
>>> cat_next_tensors = CatTensors(
...     in_keys=[("next", "observation", "observation"),
...              ("next", "observation", "achieved_goal"),
...              ("next", "observation", "desired_goal")],
...     out_key=("next", "obs")
...     )
>>> t = Compose(cat_tensors, cat_next_tensors)
>>>
>>> def func(td):
...     td = td.select(
...         "action",
...         "episode",
...         ("next", "done"),
...         ("next", "observation"),
...         ("next", "reward"),
...         ("next", "terminated"),
...         ("next", "truncated"),
...         "observation"
...         )
...     td = t(td)
...     return td
>>> with TemporaryDirectory() as tmpdir:
...     new_storage = data.preprocess(func, num_workers=4, pbar=True, mp_start_method="fork", dest=tmpdir)
...     rb = ReplayBuffer(storage=new_storage)
...     print(rb)
ReplayBuffer(
    storage=TensorStorage(
        data=TensorDict(
            fields={
                action: MemoryMappedTensor(shape=torch.Size([1000000, 8]), device=cpu, dtype=torch.float32, is_shared=True),
                episode: MemoryMappedTensor(shape=torch.Size([1000000]), device=cpu, dtype=torch.int64, is_shared=True),
                next: TensorDict(
                    fields={
                        done: MemoryMappedTensor(shape=torch.Size([1000000, 1]), device=cpu, dtype=torch.bool, is_shared=True),
                        obs: MemoryMappedTensor(shape=torch.Size([1000000, 31]), device=cpu, dtype=torch.float64, is_shared=True),
                        observation: TensorDict(
                            fields={
                            },
                            batch_size=torch.Size([1000000]),
                            device=cpu,
                            is_shared=False),
                        reward: MemoryMappedTensor(shape=torch.Size([1000000, 1]), device=cpu, dtype=torch.float64, is_shared=True),
                        terminated: MemoryMappedTensor(shape=torch.Size([1000000, 1]), device=cpu, dtype=torch.bool, is_shared=True),
                        truncated: MemoryMappedTensor(shape=torch.Size([1000000, 1]), device=cpu, dtype=torch.bool, is_shared=True)},
                    batch_size=torch.Size([1000000]),
                    device=cpu,
                    is_shared=False),
                obs: MemoryMappedTensor(shape=torch.Size([1000000, 31]), device=cpu, dtype=torch.float64, is_shared=True),
                observation: TensorDict(
                    fields={
                    },
                    batch_size=torch.Size([1000000]),
                    device=cpu,
                    is_shared=False)},
            batch_size=torch.Size([1000000]),
            device=cpu,
            is_shared=False),
        shape=torch.Size([1000000]),
        len=1000000,
        max_size=1000000),
    sampler=RandomSampler(),
    writer=RoundRobinWriter(cursor=0, full_storage=True),
    batch_size=None,
    collate_fn=<function _collate_id at 0x168406fc0>)

register_load_hook(hook: Callable[[Any], Any])

为存储注册加载钩子。

注意

目前在保存回放缓冲区时不会序列化钩子：每次创建缓冲区时都必须手动重新初始化它们。

register_save_hook(hook: Callable[[Any], Any])

为存储注册保存钩子。

注意

目前在保存回放缓冲区时不会序列化钩子：每次创建缓冲区时都必须手动重新初始化它们。

sample(batch_size: int | None = None, return_info: bool = False, include_info: bool = None) → TensorDictBase

从回放缓冲区中采样一批数据。

使用 Sampler 采样索引，并从 Storage 中检索它们。

参数：

• batch_size (int, 可选) – 要收集的数据的大小。如果未提供，则此方法将根据采样器指示采样批次大小。

• return_info (bool) – 是否返回信息。如果为 True，则结果为元组 (data, info)。如果为 False，则结果为数据。

返回值：

包含在回放缓冲区中选择的一批数据的 TensorDict。如果 return_info 标志设置为 True，则包含此 TensorDict 和信息的元组。

property sampler

回放缓冲区的采样器。

采样器必须是 Sampler 的实例。

save(*args, **kwargs)

dumps()的别名。

set_sampler(sampler: Sampler)

在回放缓冲区中设置新的采样器并返回以前的采样器。

set_storage(storage: Storage, collate_fn: Callable | None = None)

在回放缓冲区中设置新的存储并返回以前的存储。

参数：

• storage (Storage) – 缓冲区的新存储。

• collate_fn (callable, 可选) – 如果提供，则 collate_fn 设置为该值。否则将其重置为默认值。

set_writer(writer: Writer)

在回放缓冲区中设置一个新的写入器并返回之前的写入器。

property storage

回放缓冲区的存储。

存储必须是 Storage 的实例。

property writer

回放缓冲区的写入器。

写入器必须是 Writer 的实例。