CategoricalProbabilityDistribution

class maze.distributions.categorical.CategoricalProbabilityDistribution(logits: torch.Tensor, action_space: gymnasium.spaces.Discrete, temperature: float)

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: gymnasium.spaces.Discrete) Sequence[int]

(overrides TorchProbabilityDistribution)

implementation of TorchProbabilityDistribution interface