BaseDatasetExperienceReplay¶

class torchrl.data.datasets.BaseDatasetExperienceReplay(*, priority_key: str = 'td_error', **kwargs)[source]¶

離線資料集的父類。

add(data: TensorDictBase) → int¶

向回放緩衝區新增單個元素。

引數:: data (Any) – 要新增到回放緩衝區的資料
返回值:: 資料在回放緩衝區中的索引。

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

在末尾追加變換。

呼叫 sample 時，變換按順序應用。

引數:: transform (Transform) – 要追加的變換
關鍵字引數:: invert (bool, 可選) – 如果為 True，變換將被反轉（寫入時呼叫正向方法，讀取時呼叫逆向方法）。預設為 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()

abstract property data_path: Path¶: 資料集的路徑，包含分割資訊。

abstract property data_path_root: Path¶: 資料集根目錄的路徑。

delete()[source]¶: 從磁碟刪除資料集儲存。

dump(*args, **kwargs)¶: dumps() 的別名。

dumps(path)¶

將回放緩衝區儲存到磁碟上的指定路徑。

引數:: path (Path 或 str) – 儲存回放緩衝區的路徑。

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()¶: 清空回放緩衝區並將遊標重置為 0。

extend(tensordicts: TensorDictBase) → Tensor¶

使用可迭代物件中包含的一個或多個元素擴充套件回放緩衝區。

如果存在，將呼叫逆向變換。

引數:: data (可迭代物件) – 要新增到回放緩衝區的資料集合。
返回值:: 新增到回放緩衝區的資料的索引。

警告

extend() 在處理值列表時可能具有歧義的簽名，這些值列表應被解釋為 PyTree（在這種情況下，列表中的所有元素都將放入儲存中儲存的 PyTree 的一個切片中），或者要逐個新增的值列表。為了解決這個問題，TorchRL 在 list 和 tuple 之間做了明確區分：tuple 將被視為 PyTree，list（在根級別）將被解釋為要逐個新增到緩衝區的值棧。對於 ListStorage 例項，只能提供未繫結的元素（不能提供 PyTree）。

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

插入變換。

呼叫 sample 時，變換按順序執行。

引數:

index (int) – 插入變換的位置。
transform (Transform) – 要追加的變換

關鍵字引數:

invert (bool, 可選) – 如果為 True，變換將被反轉（寫入時呼叫正向方法，讀取時呼叫逆向方法）。預設為 False。

load(*args, **kwargs)¶: loads() 的別名。

loads(path)¶

載入給定路徑下的回放緩衝區狀態。

緩衝區應具有匹配的元件，並且使用 dumps() 方法儲存。

引數:: path (Path 或 str) – 儲存回放緩衝區的路徑。

更多資訊請參見 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, num_frames: int | None = None, dest: str | Path) → TensorStorage[source]¶

預處理資料集，並返回包含格式化資料的新儲存。

資料變換必須是單元式的（作用於資料集的單個樣本）。

Args 和 Keyword Args 將轉發給 map() 方法。

資料集隨後可以使用 delete() 方法刪除。

關鍵字引數:

dest (路徑或 等效物件) – 新資料集的儲存位置路徑。
num_frames (int, 可選) – 如果提供，將僅變換前 num_frames 個幀。這對於初步除錯變換非常有用。

返回值: 可在 ReplayBuffer 例項中使用的新儲存。

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])¶: 為儲存註冊載入鉤子函式。

注意

當前，鉤子函式在儲存回放緩衝區時不會被序列化：每次建立緩衝區時都必須手動重新初始化它們。

register_save_hook(hook: Callable[[Any], Any])¶: 為儲存註冊儲存鉤子函式。

注意

當前，鉤子函式在儲存回放緩衝區時不會被序列化：每次建立緩衝區時都必須手動重新初始化它們。

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

從回放緩衝區中取樣一批資料。

使用 Sampler 取樣索引，然後從 Storage 中檢索資料。

引數:

batch_size (int, 可選) – 要收集的資料大小。如果未提供，此方法將按取樣器指示的批次大小進行取樣。
return_info (bool) – 是否返回資訊。如果為 True，結果是一個元組 (data, info)。如果為 False，結果是 data。

返回值:

一個包含從回放緩衝區中選取的批次資料的 tensordict。如果 return_info 標誌設定為 True，則返回包含此 tensordict 和 info 的元組。

property sampler¶

回放緩衝區的取樣器。

取樣器必須是 Sampler 的例項。

save(*args, **kwargs)¶: dumps() 的別名。

set_sampler(sampler: Sampler)¶: 在回放緩衝區中設定新的取樣器並返回之前的取樣器。

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

在回放緩衝區中設定新的儲存並返回之前的儲存。

引數:

storage (Storage) – 緩衝區的新儲存。
collate_fn (callable, 可選) – 如果提供，則 collate_fn 設定為此值。否則，它將被重置為預設值。

set_writer(writer: Writer)¶: 在回放緩衝區中設定新的寫入器並返回之前的寫入器。

property storage¶

回放緩衝區的儲存。

儲存必須是 Storage 的例項。

property write_count¶: 透過 add 和 extend 方法寫入緩衝區至今的總項數。

property writer¶

回放緩衝區的寫入器。

寫入器必須是 Writer 的例項。

BaseDatasetExperienceReplay¶

文件

教程

資源