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 体验回放类。

Atari DQN 数据集（https://offline-rl.github.io/）是 DQN 在每个 Atari 2600 游戏上进行 5 次训练迭代的集合，总计 2 亿帧。子采样率（帧跳过）为 4，意味着每个游戏数据集共有 5000 万步。

数据格式遵循 TED 约定。由于数据集相当大，数据格式化是在采样时在线进行的。

为了使训练更具模块化，我们将 Atari 游戏中的数据集分开，并将每个训练轮次分开。因此，每个数据集都被表示为一个长度为 50x10^6 的 Storage。在底层，该数据集被分成 50 个长度为 100 万的内存映射 tensordicts。

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) – 采样期间使用的批次大小。如果需要，可以通过 data.sample(batch_size) 覆盖。

关键字参数:

• root (Path 或 str, optional) – AtariDQN 数据集根目录。实际数据集的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, optional) – 用于预处理的进程数。数据已下载时无效。默认为 0（不使用多进程）。

• download (bool 或 str, optional) – 如果找不到数据集，是否应下载。默认为 True。下载也可以传递为 "force"，在这种情况下，下载的数据将被覆盖。

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

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

• collate_fn (callable, 可选) – 将样本列表合并以形成 Tensor(s)/输出的 mini-batch。在从 map 风格的数据集进行批处理加载时使用。

• pin_memory (bool) – 是否应对 rb 样本调用 pin_memory()。

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

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

• num_slices (int, optional) – 要采样的切片数。批次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, optional) – 要采样的切片长度。批次大小必须大于或等于 slice_len 参数，并且可被其整除。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, optional) – 如果为 False，则允许批次中出现长度小于 slice_len（或 batch_size // num_slices）的轨迹。请注意，这可能导致实际 batch_size 短于要求的 batch_size！可以使用 torchrl.collectors.split_trajectories() 来拆分轨迹。默认为 True。sampler 参数将覆盖此值。

• replacement (bool, optional) – 如果为 False，则采样将无放回地进行。sampler 参数将覆盖此值。

• mp_start_method (str, optional) – 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) – 数据集名称。

• episodes (torch.Tensor) – 一个一维张量，指示这 100 万帧中的每一帧属于哪个运行。用于 SliceSampler 以低成本采样轨迹切片。

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 不提供终止信号后的下一观察。换句话说，当 ("next", "done") 为 True 时，无法获得 ("next", "observation") 状态。此值填充为 0，但不应在实践中使用。如果使用 TorchRL 的值估计器（ValueEstimator），这不应成为问题。

注意

由于用于轨迹采样的采样器构造有些复杂，我们方便用户直接将 SliceSampler 的参数传递给 AtariDQNExperienceReplay 数据集：任何 num_slices 或 slice_len 参数都会使采样器成为 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

一如既往，数据集应使用 ReplayBufferEnsemble 进行组合。

>>> 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

将单个元素添加到重放缓冲区。

参数:

data (Any) – 要添加到重放缓冲区的数据

返回:

数据在重放缓冲区中的索引。

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

将变换附加到末尾。

调用 sample 时按顺序应用变换。

参数:

transform (Transform) – 要附加的变换

关键字参数:

invert (bool, optional) – 如果为 True，则转换将被反转（前向调用将在写入时调用，反向调用将在读取时调用）。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()

classmethod as_remote(remote_config=None)

创建一个远程 ray 类的实例。

参数:

• cls (Python Class) – 要远程实例化的类。

• remote_config (dict) – 为该类保留的 CPU 核心数量。默认为 torchrl.collectors.distributed.ray.DEFAULT_REMOTE_CLASS_CONFIG。

返回:

一个创建 ray 远程类实例的函数。

property batch_size

重放缓冲区的批次大小。

批次大小可以通过在 sample() 方法中设置 batch_size 参数来覆盖。

它定义了 sample() 返回的样本数量以及 ReplayBuffer 迭代器生成的样本数量。

abstract property data_path: Path

数据集路径，包括分割。

abstract property data_path_root: Path

数据集根目录路径。

delete()

从磁盘删除数据集存储。

dump(*args, **kwargs)

等同于 dumps()。

dumps(path)

将重放缓冲区保存到指定路径的磁盘上。

参数:

path (Path 或 str) – 保存重放缓冲区的路径。

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(empty_write_count: bool = True)

清空重放缓冲区并将游标重置为 0。

参数:

empty_write_count (bool, optional) – 是否清空 write_count 属性。默认为 True。

extend(tensordicts: TensorDictBase, *, update_priority: bool | None = None) → torch.Tensor

使用数据批次扩展重放缓冲区。

参数:

tensordicts (TensorDictBase) – 用于扩展重放缓冲区的数据。

关键字参数:

update_priority (bool, optional) – 是否更新数据的优先级。默认为 True。

返回:

已添加到重放缓冲区的数据的索引。

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

插入变换。

调用 sample 时按顺序执行变换。

参数:

• index (int) – 插入变换的位置。

• transform (Transform) – 要附加的变换

关键字参数:

invert (bool, optional) – 如果为 True，则转换将被反转（前向调用将在写入时调用，反向调用将在读取时调用）。默认为 False。

load(*args, **kwargs)

等同于 loads()。

loads(path)

在给定路径加载重放缓冲区状态。

缓冲区应具有匹配的组件，并使用 dumps() 保存。

参数:

path (Path 或 str) – 重放缓冲区保存的路径。

有关更多信息，请参阅 dumps()。

next()

返回重放缓冲区的下一个项。

此方法用于在 __iter__ 不可用的情况下迭代重放缓冲区，例如 RayReplayBuffer。

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一个包含格式化数据的新存储。

数据转换必须是单位化的（作用于数据集的单个样本）。

Args 和 Keyword Args 会转发给 map()。

数据集随后可以使用 delete() 删除。

关键字参数:

• dest (path 或 等价物) – 新数据集位置的路径。

• num_frames (int, 可选) – 如果提供，则仅转换前 num_frames 帧。这对于调试转换很有用。

返回：一个将在 ReplayBuffer 实例中使用的新的 storage。

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

钩子目前不会在保存重放缓冲区时序列化：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

钩子目前不会在保存重放缓冲区时序列化：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 = None) → TensorDictBase

从重放缓冲区中采样数据批次。

使用 Sampler 采样索引，并从 Storage 中检索它们。

参数:

• batch_size (int, optional) – 要收集的数据的大小。如果未提供，此方法将采样由采样器指示的批次大小。

• 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:

一个包含在重放缓冲区中选择的数据批次的 tensordict。如果 return_info 标志设置为 True，则包含此 tensordict 和信息的元组。

property sampler

重放缓冲区的采样器。

采样器必须是 Sampler 的实例。

save(*args, **kwargs)

等同于 dumps()。

set_sampler(sampler: Sampler)

在重放缓冲区中设置新的采样器并返回之前的采样器。

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

在重放缓冲区中设置新的存储并返回之前的存储。

参数:

• storage (Storage) – 缓冲区的新的存储。

• collate_fn (callable, optional) – 如果提供，collate_fn 将设置为此值。否则，它将被重置为默认值。

set_writer(writer: Writer)

在重放缓冲区中设置新的写入器并返回之前的写入器。

property storage

重放缓冲区的存储。

Storage 必须是 Storage 的实例。

property write_count

通过 add 和 extend 写入缓冲区的总项数。

property writer

重放缓冲区的写入器。

Writer 必须是 Writer 的实例。