CoreEnv¶
-
class
maze.core.env.core_env.
CoreEnv
¶ Interface definition for core environments forming the basis for actual RL trainable environments.
-
abstract
actor_id
() → Tuple[Union[str, int], int]¶ Returns the currently executed actor along with the policy id. The id is unique only with respect to the policies (every policy has its own actor 0).
Note that identities of done actors can not be reused in the same rollout.
- Returns
The current actor, as tuple (policy id, actor number).
-
get_kpi_calculator
() → Optional[maze.core.log_events.kpi_calculator.KpiCalculator]¶ By default, Core Envs do not have to support KPIs.
-
abstract
get_maze_state
() → Any¶ Return current state of the environment.
:return The same state as returned by reset().
-
abstract
get_renderer
() → maze.core.rendering.renderer.Renderer¶ Return renderer instance that can be used to render the env.
:return Renderer instance
-
abstract
get_serializable_components
() → Dict[str, Any]¶ List components that should be serialized as part of trajectory data.
-
get_step_events
() → Iterable[maze.core.events.event_record.EventRecord]¶ Get all events recorded in the current step from the EventService.
:return An iterable of the recorded events.
-
abstract
is_actor_done
() → bool¶ Returns True if the just stepped actor is done, which is different to the done flag of the environment.
- Returns
True if the actor is done.
-
abstract
reset
() → Any¶ Reset the environment and return initial state.
- Returns
The initial state after resetting.
-
abstract
seed
(seed: int) → None¶ Sets the seed for this environment’s random number generator(s).
- Param
seed: the seed integer initializing the random number generator.
-
abstract
step
(maze_action: Any) → Tuple[Any, Union[float, numpy.ndarray, Any], bool, Dict[Any, Any]]¶ Environment step function.
- Parameters
maze_action – Environment MazeAction to take.
- Returns
state, reward, done, info
-
abstract