This repository contains a customizable gym environment for all kinds of mazes or gridworlds. The motivation of this repository is, as maze or gridworld are used very often in the reinforcement learning community, however, it is still lack of a standardized framework.
The repo will be actively maintained, any comments, feedbacks or improvements are highly welcomed.
This repository requires following packages:
- gym >= 0.9.4
- Python >= 3.6
- Numpy >= 1.13.3
- Matplotlib >= 2.1.1
- Scikit-image >= 0.13.1
- (Recommended) JupyterLab >= 0.31.0
cd gym_maze
pip install -e .We have provided a Jupyter Notebook to illustrate how to make various of maze environments, and generate animation of the agent's trajectory following the optimal actions solved by A* optimal planner.
- Maze generator: You can define your own maze generator, simply by creating a class inherited from base class
MazeGeneratorand the class should look like at least:
class NewMazeGenerator(MazeGenerator):
def __init__(self, args...):
super().__init__()
self.maze = ...
...
def sample_state(self):
...
- Maze solver: You can define your own maze solver. For now, please take a look at the code of
Astar_solver.py.
- More extensive documentations
- More different kinds of mazes