CategoricalProbabilityDistribution

class maze.distributions.categorical.CategoricalProbabilityDistribution(*args, **kwds)

Categorical Torch probability distribution.

Parameters

logits – the action selection logits.

deterministic_sample()

(overrides TorchProbabilityDistribution)

implementation of ProbabilityDistribution interface

log_prob(actions: torch.Tensor)torch.Tensor

(overrides TorchProbabilityDistribution)

implementation of ProbabilityDistribution interface

classmethod required_logits_shape(action_space: gym.spaces.Discrete) → Sequence[int]

(overrides TorchProbabilityDistribution)

implementation of TorchProbabilityDistribution interface