unienv_data.batches.combined_batch

CombinedBatch

CombinedBatch(batches: Sequence[BatchBase[BatchT, BArrayType, BDeviceType, BDtypeType, BRNGType]], device: Optional[BDeviceType] = None, use_thread_pool: bool = False)

Bases: BatchBase[BatchT, BArrayType, BDeviceType, BDtypeType, BRNGType]

is_mutable instance-attribute

is_mutable = is_mutable

batches instance-attribute

batches = batches

use_thread_pool instance-attribute

use_thread_pool = use_thread_pool

single_space instance-attribute

single_space = single_space

single_metadata_space instance-attribute

single_metadata_space = single_metadata_space

backend property

backend: ComputeBackend[BArrayType, BDeviceType, BDtypeType, BRNGType]

device property

device: Optional[BDeviceType]

get_column

get_column(nested_keys: Sequence[Any]) -> BatchBase

Lazy view over one field of the samples that combines the children's column views, so that children able to read a single column cheaply (replay buffers, stacked views, ...) do so instead of fetching whole samples. Values, spaces, metadata and the flattened layout are those of SubItemBatch(self, nested_keys), which is returned when the children's column views cannot be combined. The view is read-only.

get_flattened_at

get_flattened_at(idx: Union[IndexableType, BaseException]) -> BArrayType

get_flattened_at_with_metadata

get_flattened_at_with_metadata(idx: Union[IndexableType, BaseException]) -> Tuple[BArrayType, Dict[str, Any]]

get_at

get_at(idx: Union[IndexableType, BArrayType]) -> BatchT

get_at_with_metadata

get_at_with_metadata(idx: Union[IndexableType, BArrayType]) -> Tuple[BatchT, Dict[str, Any]]

set_flattened_at

set_flattened_at(idx: Union[IndexableType, BArrayType], value: BArrayType) -> None

extend_flattened

extend_flattened(value: BArrayType) -> None

set_at

set_at(idx: Union[IndexableType, BArrayType], value: BatchT) -> None

remove_at

remove_at(idx: Union[IndexableType, BArrayType]) -> None

extend

extend(value: BatchT) -> None

close

close() -> None

Release this view. The child batches are not owned by the view and stay open; close them through whoever created it (BatchBase.__del__ calls close(), so closing the children here would tear it down whenever a view is garbage-collected).

append_flattened

append_flattened(value: BArrayType) -> None

Append one flattened sample to the batch.

append

append(value: BatchT) -> None

Append one structured sample to the batch.

extend_from

extend_from(other: BatchBase[BatchT, BArrayType, BDeviceType, BDtypeType, BRNGType], chunk_size: int = 8, tqdm: bool = False) -> None

Copy data from another batch in bounded-size chunks.

get_slice

get_slice(idx: Union[IndexableType, BArrayType]) -> BatchBase[BatchT, BArrayType, BDeviceType, BDtypeType, BRNGType]

Create a lazy view over a subset of indices.

convert_single_index_to_batch

convert_single_index_to_batch(backend: ComputeBackend, index_starts: BArrayType, total_length: int, idx: int, device: Optional[BDeviceType] = None) -> Tuple[int, int]

Convert a single index for this batch to a tuple of

• The index of the batch
• The index to index into the batch

convert_index_to_batch

convert_index_to_batch(backend: ComputeBackend, index_starts: BArrayType, total_length: int, idx: Union[IndexableType, BArrayType], device: Optional[BDeviceType] = None) -> Tuple[int, Union[List[Tuple[int, BArrayType, BArrayType]], int]]

Convert an index for this batch to a tuple of

• The length of the resulting array
• List of tuples, each containing:
  • The index of the batch
  • The index to index into the batch
  • The bool mask to index into the resulting array