ProbabilisticPolicyComposer

class maze.perception.models.policies.probabilistic_policy_composer.ProbabilisticPolicyComposer(action_spaces_dict: Dict[str | int, gymnasium.spaces.Dict], observation_spaces_dict: Dict[str | int, gymnasium.spaces.Dict], agent_counts_dict: Dict[str | int, int], distribution_mapper: DistributionMapper, networks: List[None | Mapping[str, Any] | Any] | Mapping[str | Type, None | Mapping[str, Any] | Any], substeps_with_separate_agent_nets: List[str | int])

Composes networks for probabilistic policies.

Parameters:

• action_spaces_dict – Dict of sub-step id to action space.

• observation_spaces_dict – Dict of sub-step id to observation space.

• distribution_mapper – The distribution mapper.

• networks – Policy networks as defined in the config (either list or dictionary of object params and type).

property policy: TorchPolicy

implementation of BasePolicyComposer