`hyphi_gym.envs.GridMaze`#

Package Contents#

Classes#

`Grid`	Base for grid-based games managing
`Maze`	Gridworld Maze Environment based on hyphi Grid.
`GridMaze`	Gridworld Maze Environment based on hyphi Grid.

class hyphi_gym.envs.GridMaze.Grid(render_mode: hyphi_gym.common.board.Optional[str] = None, **simargs)#

Bases: hyphi_gym.common.rendering.Rendering, hyphi_gym.common.point.Point

Base for grid-based games managing • A layout of a variable size • Containing CELLS ∈ [WALL, FIELD, AGENT, TARGET, HOLE] • Navigable with ACTIONS ∈ [UP, RIGHT, DOWN,LEFT]

step_scale = 1#

base_xml#

metadata#

render() → hyphi_gym.common.board.Optional[hyphi_gym.common.board.np.ndarray]#: Return rendering of current state as np array if render_mode set

reset(**kwargs) → tuple[hyphi_gym.common.board.np.ndarray, dict]#: Gymnasium compliant function to reset the environment

_distance()#

execute(action: int) → tuple[hyphi_gym.common.board.np.ndarray, dict]#: Helper function to step the environment, executing action, returning its consequences

class hyphi_gym.envs.GridMaze.Maze(size, random=[], prefix='', **kwargs)#

Bases: hyphi_gym.common.board.Board

Gridworld Maze Environment based on hyphi Grid. :param size: (≤15, guarantee solvability within 100 steps (worst for 15: 96)) :param random: optional list of features to be stochastic supporting layout, agent-, and target-placement

_generate()#: Generate random mazes of self.size using Kruskal’s algorithm. Generated mazes are forced to difer the static configurations above.

class hyphi_gym.envs.GridMaze.GridMaze(render_mode=None, **kwargs)#

Bases: hyphi_gym.common.maze.Maze, hyphi_gym.common.grid.Grid

hyphi_gym.envs.GridMaze#

Package Contents#

Classes#

`hyphi_gym.envs.GridMaze`#