A simple 2D maze environment where an agent (blue dot) finds its way from the top left corner (blue square) to the goal at the bottom right corner (red square). The objective is to find the shortest path from the start to the goal.

The agent may only choose to go up, down, right, or left ("N", "S", "E", "W"). If the way is blocked, it will remain at the same the location.

The observation space is the (x, y) coordinate of the agent. The top left cell is (0, 0).

A reward of 1 is given when the agent reaches the goal. For every step in the maze, the agent recieves a reward of -0.1/(number of cells).

The maze is reset when the agent reaches the goal.

• 3 cells x 3 cells: MazeEnvSample3x3
• 5 cells x 5 cells: MazeEnvSample5x5
• 10 cells x 10 cells: MazeEnvSample10x10
• 100 cells x 100 cells: MazeEnvSample100x100

• 3 cells x 3 cells: MazeEnvRandom3x3
• 5 cells x 5 cells: MazeEnvRandom5x5
• 10 cells x 10 cells: MazeEnvRandom10x10
• 100 cells x 100 cells: MazeEnvRandom100x100

With loops, it means that there will be more than one possible path. The agent can also teleport from a portal to another portal of the same colour.

• 10 cells x 10 cells: MazeEnvRandom10x10Plus
• 20 cells x 20 cells: MazeEnvRandom20x20Plus
• 30 cells x 30 cells: MazeEnvRandom30x30Plus

It should work on both Python 2.7+ and 3.4+. It requires pygame and numpy.

cd gym-maze
python setup.py install

An example of finding the shortest path through the maze using Q-learning can be found here: https://github.com/tuzzer/ai-gym/blob/master/maze_2d/maze_2d_q_learning.py