ActionConversionInterface¶
-
class
maze.core.env.action_conversion.
ActionConversionInterface
¶ Interface specifying the conversion of agent actions to actual environment MazeActions.
-
maze_to_space
(maze_action: Any) → Dict[str, numpy.ndarray]¶ Converts environment MazeAction to agent action.
- Parameters
maze_action – the environment MazeAction.
- Returns
the agent action.
-
noop_action
()¶ Converts environment MazeAction to agent action.
- Returns
the noop action.
-
abstract
space
() → gym.spaces.Dict¶ Returns respective gym action space.
-
abstract
space_to_maze
(action: Dict[str, numpy.ndarray], maze_state: Any) → Any¶ Converts agent action to environment MazeAction.
- Parameters
action – the agent action.
maze_state – the environment state.
- Returns
the environment MazeAction.
-