Delta¶
- class torchrl.modules.Delta(param: Tensor, atol: float = 1e-06, rtol: float = 1e-06, batch_shape: Optional[Union[Size, Sequence[int]]] = None, event_shape: Optional[Union[Size, Sequence[int]]] = None)[source]¶
Delta distribution.
- Parameters:
param (torch.Tensor) – parameter of the delta distribution;
atol (number, optional) – absolute tolerance to consider that a tensor matches the distribution parameter; Default is 1e-6
rtol (number, optional) – relative tolerance to consider that a tensor matches the distribution parameter; Default is 1e-6
batch_shape (torch.Size, optional) – batch shape;
event_shape (torch.Size, optional) – shape of the outcome.
- expand(batch_shape: Size, _instance=None)[source]¶
Returns a new distribution instance (or populates an existing instance provided by a derived class) with batch dimensions expanded to batch_shape. This method calls
expand
on the distribution’s parameters. As such, this does not allocate new memory for the expanded distribution instance. Additionally, this does not repeat any args checking or parameter broadcasting in __init__.py, when an instance is first created.- Parameters:
batch_shape (torch.Size) – the desired expanded size.
_instance – new instance provided by subclasses that need to override .expand.
- Returns:
New distribution instance with batch dimensions expanded to batch_size.
- log_prob(value: Tensor) Tensor [source]¶
Returns the log of the probability density/mass function evaluated at value.
- Parameters:
value (Tensor) –