TorchStepStateCritic

class maze.core.agent.torch_state_critic.TorchStepStateCritic(networks: Mapping[Union[str, int], torch.nn.Module], num_policies: int, device: str)

Each sub-step or actor gets its individual critic. Can be instantiated via the StepStateCriticComposer.

property num_critics

implementation of TorchStateCritic

predict_values(observations: Dict[Union[str, int], Dict[str, torch.Tensor]]) → Tuple[Dict[Union[str, int], torch.Tensor], Dict[Union[str, int], torch.Tensor]]

implementation of StateCritic