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.

Room Id	Grid-Size	Pixels	#Boxes	Example	TinyWorld
Sokoban-v0	10x10	160x160	3
Sokoban-v1	10x10	160x160	4
Sokoban-v2	10x10	160x160	5
Sokoban-small-v0	7x7	112x112	2
Sokoban-small-v1	7x7	112x112	3
Sokoban-large-v0	13x11	208x176	3
Sokoban-large-v1	13x11	208x176	4
Sokoban-large-v2	13x11	208x176	5
Sokoban-huge-v0	13x13	208x208	5

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!