StateCritic¶
-
class
maze.core.agent.state_critic.StateCritic¶ Structured state critic class designed to work with structured environments. (see
StructuredEnv).It encapsulates state critic and queries them for values according to the provided policy ID.
-
abstract
predict_value(observation: Dict[str, numpy.ndarray], critic_id: Union[int, str]) → torch.Tensor¶ Query a critic that corresponds to the given ID for the state value.
- Parameters
observation – Current observation of the environment
critic_id – The critic id to query
- Returns
The value for this observation
-
abstract
predict_values(observations: Dict[Union[str, int], Dict[str, numpy.ndarray]]) → Tuple[Dict[Union[str, int], torch.Tensor], Dict[Union[str, int], torch.Tensor]]¶ Query a critic that corresponds to the given ID for the state value.
- Parameters
observations – Current observation of the environment
- Returns
Tuple containing the values and detached values
-
abstract