BernoulliProbabilityDistribution¶
- class maze.distributions.bernoulli.BernoulliProbabilityDistribution(logits: torch.Tensor, action_space: gymnasium.spaces.MultiBinary, temperature: float = 1.0)¶
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¶
(overrides
TorchProbabilityDistribution)implementation of
ProbabilityDistributioninterface
- entropy() torch.Tensor¶
(overrides
TorchProbabilityDistribution)implementation of
ProbabilityDistributioninterface
- kl(other: TorchProbabilityDistribution) torch.Tensor¶
(overrides
TorchProbabilityDistribution)implementation of
ProbabilityDistributioninterface
- log_prob(actions: torch.Tensor) torch.Tensor¶
(overrides
TorchProbabilityDistribution)implementation of
ProbabilityDistributioninterface
- classmethod required_logits_shape(action_space: gymnasium.spaces.MultiBinary) Sequence[int]¶
(overrides
TorchProbabilityDistribution)implementation of
TorchProbabilityDistributioninterface