BernoulliProbabilityDistribution¶
-
class
maze.distributions.bernoulli.BernoulliProbabilityDistribution(*args, **kwds)¶ Bernoulli Torch probability distribution for multi-binary action spaces.
- Parameters
logits – the action selection logits.
action_space – The gym action space.
temperature – The distribution temperature parameter.
-
deterministic_sample() → torch.Tensor¶ implementation of
ProbabilityDistributioninterface
-
entropy() → torch.Tensor¶ implementation of
ProbabilityDistributioninterface
-
kl(other: maze.distributions.torch_dist.TorchProbabilityDistribution) → torch.Tensor¶ implementation of
ProbabilityDistributioninterface
-
log_prob(actions: torch.Tensor) → torch.Tensor¶ implementation of
ProbabilityDistributioninterface
-
classmethod
required_logits_shape(action_space: gym.spaces.MultiBinary) → Sequence[int]¶ implementation of
TorchProbabilityDistributioninterface