DiagonalGaussianProbabilityDistribution

class maze.distributions.gaussian.DiagonalGaussianProbabilityDistribution(logits: torch.Tensor, action_space: gymnasium.spaces.Box, temperature: float)

Diagonal Gaussian (Normal) Torch probability distribution.

Parameters:

logits – The logits for both mean and standard deviation.

deterministic_sample() → torch.Tensor

(overrides TorchProbabilityDistribution)

implementation of TorchProbabilityDistribution interface

entropy() → torch.Tensor

(overrides TorchProbabilityDistribution)

implementation of TorchProbabilityDistribution interface

kl(other: TorchProbabilityDistribution) → torch.Tensor

(overrides TorchProbabilityDistribution)

implementation of TorchProbabilityDistribution interface

log_prob(actions: torch.Tensor) → torch.Tensor

(overrides TorchProbabilityDistribution)

implementation of TorchProbabilityDistribution interface

classmethod required_logits_shape(action_space: gymnasium.spaces.Space) → Sequence[int]

(overrides TorchProbabilityDistribution)

implementation of TorchProbabilityDistribution interface