LazyStackedCompositeSpec

class torchrl.data.LazyStackedCompositeSpec(*specs: tuple[T, ...], dim: int)

A lazy representation of a stack of composite specs.

Stacks composite specs together along one dimension. When random samples are drawn, a LazyStackedTensorDict is returned.

Indexing is allowed but only along the stack dimension.

This class is aimed to be used in multi-task and multi-agent settings, where heterogeneous specs may occur (same semantic but different shape).

assert_is_in(value: Tensor) → None

Asserts whether a tensor belongs to the box, and raises an exception otherwise.

Parameters:

value (torch.Tensor) – value to be checked.

clear_device_()

Clears the device of the CompositeSpec.

empty()

Create a spec like self, but with no entries.

encode(vals: Dict[str, Any], ignore_device: bool = False) → Dict[str, Tensor]

Encodes a value given the specified spec, and return the corresponding tensor.

Parameters:

val (np.ndarray or torch.Tensor) – value to be encoded as tensor.

Keyword Arguments:

ignore_device (bool, optional) – if True, the spec device will be ignored. This is used to group tensor casting within a call to TensorDict(..., device="cuda") which is faster.

Returns:

torch.Tensor matching the required tensor specs.

expand(*shape)

Returns a new Spec with the extended shape.

Parameters:

*shape (tuple or iterable of int) – the new shape of the Spec. Must comply with the current shape: its length must be at least as long as the current shape length, and its last values must be complient too; ie they can only differ from it if the current dimension is a singleton.

flatten(start_dim, end_dim)

Flattens a tensorspec.

Check flatten() for more information on this method.

get(item, default=<object object>)

Gets an item from the CompositeSpec.

If the item is absent, a default value can be passed.

classmethod implements_for_spec(torch_function: Callable) → Callable

Register a torch function override for TensorSpec.

abstract index(index: Union[int, Tensor, ndarray, slice, List], tensor_to_index: Tensor) → Tensor

Indexes the input tensor.

Parameters:

• index (int, torch.Tensor, slice or list) – index of the tensor

• tensor_to_index – tensor to be indexed

Returns:

indexed tensor

is_empty()

Whether the composite spec contains specs or not.

is_in(val) → bool

If the value val is in the box defined by the TensorSpec, returns True, otherwise False.

Parameters:

val (torch.Tensor) – value to be checked

Returns:

boolean indicating if values belongs to the TensorSpec box

items(include_nested: bool = False, leaves_only: bool = False)

Items of the CompositeSpec.

Parameters:

• include_nested (bool, optional) – if False, the returned keys will not be nested. They will represent only the immediate children of the root, and not the whole nested sequence, i.e. a CompositeSpec(next=CompositeSpec(obs=None)) will lead to the keys ["next"]. Default is ``False`, i.e. nested keys will not be returned.

• leaves_only (bool, optional) – if False, the values returned will contain every level of nesting, i.e. a CompositeSpec(next=CompositeSpec(obs=None)) will lead to the keys ["next", ("next", "obs")]. Default is False.

keys(include_nested: bool = False, leaves_only: bool = False) → KeysView

Keys of the CompositeSpec.

The keys argument reflect those of tensordict.TensorDict.

Parameters:

• include_nested (bool, optional) – if False, the returned keys will not be nested. They will represent only the immediate children of the root, and not the whole nested sequence, i.e. a CompositeSpec(next=CompositeSpec(obs=None)) will lead to the keys ["next"]. Default is ``False`, i.e. nested keys will not be returned.

• leaves_only (bool, optional) – if False, the values returned will contain every level of nesting, i.e. a CompositeSpec(next=CompositeSpec(obs=None)) will lead to the keys ["next", ("next", "obs")]. Default is False.

lock_(recurse=False)

Locks the CompositeSpec and prevents modification of its content.

This is only a first-level lock, unless specified otherwise through the recurse arg.

Leaf specs can always be modified in place, but they cannot be replaced in their CompositeSpec parent.

Examples

>>> shape = [3, 4, 5]
>>> spec = CompositeSpec(
...         a=CompositeSpec(
...         b=CompositeSpec(shape=shape[:3], device="cpu"), shape=shape[:2]
...     ),
...     shape=shape[:1],
... )
>>> spec["a"] = spec["a"].clone()
>>> recurse = False
>>> spec.lock_(recurse=recurse)
>>> try:
...     spec["a"] = spec["a"].clone()
... except RuntimeError:
...     print("failed!")
failed!
>>> try:
...     spec["a", "b"] = spec["a", "b"].clone()
...     print("succeeded!")
... except RuntimeError:
...     print("failed!")
succeeded!
>>> recurse = True
>>> spec.lock_(recurse=recurse)
>>> try:
...     spec["a", "b"] = spec["a", "b"].clone()
...     print("succeeded!")
... except RuntimeError:
...     print("failed!")
failed!

project(val: TensorDictBase) → TensorDictBase

If the input tensor is not in the TensorSpec box, it maps it back to it given some heuristic.

Parameters:

val (torch.Tensor) – tensor to be mapped to the box.

Returns:

a torch.Tensor belonging to the TensorSpec box.

rand(shape=None) → TensorDictBase

Returns a random tensor in the box. The sampling will be uniform unless the box is unbounded.

Parameters:

shape (torch.Size) – shape of the random tensor

Returns:

a random tensor sampled in the TensorSpec box.

reshape(*shape)

Reshapes a tensorspec.

Check reshape() for more information on this method.

squeeze(dim: Optional[int] = None)

Returns a new Spec with all the dimensions of size 1 removed.

When dim is given, a squeeze operation is done only in that dimension.

Parameters:

dim (int or None) – the dimension to apply the squeeze operation to

to_numpy(val: TensorDict, safe: Optional[bool] = None) → dict

Returns the np.ndarray correspondent of an input tensor.

Parameters:

• val (torch.Tensor) – tensor to be transformed_in to numpy.

• safe (bool) – boolean value indicating whether a check should be performed on the value against the domain of the spec. Defaults to the value of the CHECK_SPEC_ENCODE environment variable.

Returns:

a np.ndarray

type_check(value: Union[Tensor, TensorDictBase], selected_keys: Optional[Union[str, Tuple[str, ...], Sequence[Union[str, Tuple[str, ...]]]]] = None)

Checks the input value dtype against the TensorSpec dtype and raises an exception if they don’t match.

Parameters:

• value (torch.Tensor) – tensor whose dtype has to be checked

• key (str, optional) – if the TensorSpec has keys, the value dtype will be checked against the spec pointed by the indicated key.

unflatten(dim, sizes)

Unflattens a tensorspec.

Check unflatten() for more information on this method.

unlock_(recurse=False)

Unlocks the CompositeSpec and allows modification of its content.

This is only a first-level lock modification, unless specified otherwise through the recurse arg.

values(include_nested: bool = False, leaves_only: bool = False)

Values of the CompositeSpec.

Parameters:

• include_nested (bool, optional) – if False, the returned keys will not be nested. They will represent only the immediate children of the root, and not the whole nested sequence, i.e. a CompositeSpec(next=CompositeSpec(obs=None)) will lead to the keys ["next"]. Default is ``False`, i.e. nested keys will not be returned.

• leaves_only (bool, optional) – if False, the values returned will contain every level of nesting, i.e. a CompositeSpec(next=CompositeSpec(obs=None)) will lead to the keys ["next", ("next", "obs")]. Default is False.

view(*shape)

Reshapes a tensorspec.

Check reshape() for more information on this method.

zero(shape=None) → TensorDictBase

Returns a zero-filled tensor in the box.

Parameters:

shape (torch.Size) – shape of the zero-tensor

Returns:

a zero-filled tensor sampled in the TensorSpec box.