StateCriticStepOutput

class maze.core.agent.state_critic_input_output.StateCriticStepOutput(values: torch.Tensor, detached_values: torch.Tensor, actor_id: maze.core.env.structured_env.ActorID)

State Critic Step output holds the output of an a critic for an individual env step.

actor_id: maze.core.env.structured_env.ActorID

The actor id of the actor corresponding to this critic output.

detached_values: torch.Tensor

The computed detached values.

values: torch.Tensor

The computed values.