MinariExperienceReplay¶

class torchrl.data.datasets.MinariExperienceReplay(dataset_id, batch_size: int, *, root: str | Path | None = None, download: bool = True, sampler: Sampler | None = None, writer: Writer | None = None, collate_fn: Callable | None = None, pin_memory: bool = False, prefetch: int | None = None, transform: 'torchrl.envs.Transform' | None = None, split_trajs: bool = False)[source]¶

Minari 經驗回放資料集。

在他們的網站上了解更多關於 Minari 的資訊：https://minari.farama.org/

資料格式遵循 TED 慣例。

參數:

dataset_id (str) – 要下載的資料集。必須是 MinariExperienceReplay.available_datasets 的一部分
batch_size (int) – 採樣期間使用的批次大小。如有必要，可以被 data.sample(batch_size) 覆蓋。

關鍵字參數:

root (Path 或 str, optional) – Minari 資料集根目錄。實際的資料集記憶體對應檔案將儲存在 <root>/<dataset_id> 下。如果未提供，則預設為 ``~/.cache/torchrl/minari`。
download (bool 或 str, optional) – 如果找不到資料集是否應該下載。預設為 True。下載也可以作為 "force" 傳遞，在這種情況下，下載的資料將被覆蓋。
sampler (Sampler, optional) – 要使用的 sampler。如果未提供，將使用預設的 RandomSampler()。
writer (Writer, optional) – 要使用的 writer。如果未提供，將使用預設的 ImmutableDatasetWriter。
collate_fn (callable, optional) – 合併樣本列表以形成 Tensor(s)/輸出的迷你批次。從地圖樣式資料集使用批次載入時使用。
pin_memory (bool) – 是否應該在 rb 樣本上呼叫 pin_memory()。
prefetch (int, optional) – 使用多執行緒預先獲取的下一個批次的數量。
transform (Transform, optional) – 當呼叫 sample() 時要執行的 Transform。要鏈接轉換，請使用 Compose 類別。
split_trajs (bool, optional) – 若為 True，軌跡將沿著第一個維度分割，並填充至具有相符的形狀。為了分割軌跡，將使用 "done" 訊號，此訊號透過 done = truncated | terminated 恢復。換句話說，假設任何 truncated 或 terminated 訊號都等同於軌跡的結束。預設值為 False。

變數:

available_datasets – 可供下載的已接受條目的列表。

注意

文字資料目前已從封裝的資料集中捨棄，因為目前沒有 PyTorch 原生的方式來表示文字資料。如果需要此功能，請在 TorchRL 的 GitHub 儲存庫上發布 issue。

範例

>>> from torchrl.data.datasets.minari_data import MinariExperienceReplay
>>> data = MinariExperienceReplay("door-human-v1", batch_size=32, download="force")
>>> for sample in data:
...     torchrl_logger.info(sample)
...     break
TensorDict(
    fields={
        action: Tensor(shape=torch.Size([32, 28]), device=cpu, dtype=torch.float32, is_shared=False),
        index: Tensor(shape=torch.Size([32]), device=cpu, dtype=torch.int64, is_shared=False),
        info: TensorDict(
            fields={
                success: Tensor(shape=torch.Size([32]), device=cpu, dtype=torch.bool, is_shared=False)},
            batch_size=torch.Size([32]),
            device=cpu,
            is_shared=False),
        next: TensorDict(
            fields={
                done: Tensor(shape=torch.Size([32, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                info: TensorDict(
                    fields={
                        success: Tensor(shape=torch.Size([32]), device=cpu, dtype=torch.bool, is_shared=False)},
                    batch_size=torch.Size([32]),
                    device=cpu,
                    is_shared=False),
                observation: Tensor(shape=torch.Size([32, 39]), device=cpu, dtype=torch.float64, is_shared=False),
                reward: Tensor(shape=torch.Size([32, 1]), device=cpu, dtype=torch.float64, is_shared=False),
                state: TensorDict(
                    fields={
                        door_body_pos: Tensor(shape=torch.Size([32, 3]), device=cpu, dtype=torch.float64, is_shared=False),
                        qpos: Tensor(shape=torch.Size([32, 30]), device=cpu, dtype=torch.float64, is_shared=False),
                        qvel: Tensor(shape=torch.Size([32, 30]), device=cpu, dtype=torch.float64, is_shared=False)},
                    batch_size=torch.Size([32]),
                    device=cpu,
                    is_shared=False),
                terminated: Tensor(shape=torch.Size([32, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                truncated: Tensor(shape=torch.Size([32, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
            batch_size=torch.Size([32]),
            device=cpu,
            is_shared=False),
        observation: Tensor(shape=torch.Size([32, 39]), device=cpu, dtype=torch.float64, is_shared=False),
        state: TensorDict(
            fields={
                door_body_pos: Tensor(shape=torch.Size([32, 3]), device=cpu, dtype=torch.float64, is_shared=False),
                qpos: Tensor(shape=torch.Size([32, 30]), device=cpu, dtype=torch.float64, is_shared=False),
                qvel: Tensor(shape=torch.Size([32, 30]), device=cpu, dtype=torch.float64, is_shared=False)},
            batch_size=torch.Size([32]),
            device=cpu,
            is_shared=False)},
    batch_size=torch.Size([32]),
    device=cpu,
    is_shared=False)

add(data: TensorDictBase) → int¶

將單個元素新增到回放緩衝區。

參數:: data (Any) – 要新增到回放緩衝區的資料
回傳值:: 資料在回放緩衝區中的索引位置。

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

在結尾附加轉換。

當呼叫 sample 時，轉換會依序套用。

參數:: transform (Transform) – 要附加的轉換
關鍵字參數:: invert (bool, optional) – 若為 True，轉換將會反轉（正向呼叫將在寫入期間呼叫，反向呼叫將在讀取期間呼叫）。預設值為 False。

範例

>>> 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()

property data_path: Path¶: 資料集的路徑，包括分割。

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

delete()¶: 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。

參數:: path (Path or str) – 要儲存回放緩衝區的路徑。

範例

>>> 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游標重設為 0。

extend(tensordicts: TensorDictBase) → Tensor¶

使用可迭代物件中包含的一個或多個元素擴展回放緩衝區。

如果存在，將會呼叫反向轉換。

參數:: data (iterable) – 要新增到回放緩衝區的資料集合。
回傳值:: 新增到回放緩衝區的資料的索引。

警告

當處理值列表時，extend() 可能具有不明確的簽名，這些值應被解釋為 PyTree（在這種情況下，列表中的所有元素都將放置在儲存的 PyTree 中的切片中），或是一次新增一個的值列表。為了解決這個問題，TorchRL 明確區分了列表和元組：元組將被視為 PyTree，列表（在根層級）將被解釋為一次新增一個到緩衝區的值的堆疊。對於 ListStorage 實例，只能提供未綁定的元素（沒有 PyTrees）。

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

插入轉換 (transform)。

當呼叫 sample 時，轉換會依序執行。

參數:

index (int) – 插入轉換的位置。
transform (Transform) – 要附加的轉換

關鍵字參數:

invert (bool, optional) – 若為 True，轉換將會反轉（正向呼叫將在寫入期間呼叫，反向呼叫將在讀取期間呼叫）。預設值為 False。

load(*args, **kwargs)¶: 是 loads() 的別名。

loads(path)¶

在給定的路徑載入 replay buffer 的狀態。

buffer 應該有匹配的元件，並且使用 dumps() 儲存。

參數:: path (Path 或 str) – replay buffer 儲存的路徑。

更多資訊請參考 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¶

預處理資料集，並返回一個具有格式化數據的新儲存空間 (storage)。

資料轉換必須是單一的 (在資料集中的單個樣本上工作)。

Args 和 Keyword Args 會轉發到 map()。

資料集可以隨後使用 delete() 刪除。

關鍵字參數:

dest (path 或 等效路徑) – 新資料集位置的路徑。
num_frames (int, optional) – 如果提供，則只會轉換前 num_frames 個 frame。這對於首先 debug 轉換很有用。

回傳值：一個新的儲存空間，將在 ReplayBuffer 實例中使用。

範例

>>> 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])¶: 為儲存空間註冊一個載入 hook。

注意

當儲存重播緩衝區時，Hooks 目前不會被序列化：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])¶: 為儲存空間註冊一個儲存 hook。

注意

當儲存重播緩衝區時，Hooks 目前不會被序列化：每次建立緩衝區時都必須手動重新初始化它們。

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

從重播緩衝區中取樣一批資料。

使用 Sampler 來取樣索引，並從 Storage 檢索它們。

參數:

batch_size (int, optional) – 要收集的資料大小。如果沒有提供，此方法將取樣一個由 sampler 指示的 batch-size。
return_info (bool) – 是否回傳 info。如果為 True，結果是一個元組 (data, info)。如果為 False，結果是 data。

回傳值:

一個 tensordict，包含在重播緩衝區中選取的一批資料。如果 return_info 標誌設定為 True，則包含此 tensordict 和 info 的元組。

property sampler¶

重播緩衝區的 sampler。

sampler 必須是 Sampler 的一個實例。

save(*args, **kwargs)¶: dumps() 的別名。

set_sampler(sampler: Sampler)¶: 在重播緩衝區中設定一個新的 sampler，並回傳先前的 sampler。

set_storage(storage: Storage, collate_fn: Optional[Callable] = None)¶

在重播緩衝區中設定一個新的儲存空間，並回傳先前的儲存空間。

參數:

storage (Storage) – 緩衝區的新儲存空間。
collate_fn (callable, optional) – 如果提供，則 collate_fn 會設定為此值。否則，它會重置為預設值。

set_writer(writer: Writer)¶: 在重播緩衝區中設定一個新的 writer，並回傳先前的 writer。

property storage¶

重播緩衝區的儲存空間。

儲存空間必須是 Storage 的一個實例。

property write_count¶: 到目前為止，透過 add 和 extend 在緩衝區中寫入的項目總數。

property writer¶

重播緩衝區的 writer。

writer 必須是 Writer 的一個實例。

MinariExperienceReplay¶

文件

教學

資源