amaze.extensions.sb3.maze_env

SB3 wrapper for the maze environment

Functions

env_attr(env, attr)	Returns the requested attribute from each underlying environments
env_method(env, method, *args, **kwargs)	Calls a given function, with specified arguments, on each underlying environments
make_vec_maze_env(mazes, robot, seed[, ...])	Encapsulates the creation of a vectorized environment

Classes

MazeEnv(maze, robot[, log_trajectory])

AMaze wrapper for the stable baselines 3 library

amaze.extensions.sb3.maze_env.make_vec_maze_env(

mazes: List[BuildData],

robot: BuildData,

seed,

check_env=True,

**kwargs,

)

Encapsulates the creation of a vectorized environment

amaze.extensions.sb3.maze_env.env_method(env, method: str, *args, **kwargs)

Calls a given function, with specified arguments, on each underlying environments

amaze.extensions.sb3.maze_env.env_attr(env, attr: str)

Returns the requested attribute from each underlying environments

class amaze.extensions.sb3.maze_env.MazeEnv(

maze: BuildData,

robot: BuildData,

log_trajectory: bool = False,

)

AMaze wrapper for the stable baselines 3 library

reset(seed=None, options=None, full_reset=False)

Stub

step(action)

Stub docstring

render() → ndarray | None

Stub

close()

Stub

optimal_reward()

Return the cumulative reward for an agent following an optimal trajectory