A Sokoban AI solver using the gym-sokoban environment. Uses the reward values from the gym-sokoban environment to compute edge weights. The Branch and Bound algorithm was employed.
Example Game 1 | Example Game 2 | Example Game 3 |
---|---|---|
pip install gym-sokoban
git clone [email protected]:mpSchrader/gym-sokoban.git
cd gym-sokoban
pip install -e .
The available room configurations are shown in the table below.
Please note that the larger rooms might take some time to be created, especially on a laptop.
Choose any of these and import the corresponding version in the sokobanAI/sokobanAI.py
file.
Run sokobanAI/sokobanAI.py
, sit back and enjoy!