This is a simulation of Bomberman using the Reinforcement Learning technique 'Q-Learning'.
Refer Wiki for documentation.
The idea is based on the the article "Deep Reinforcement Learning for Maze Solving" http://www.samyzaf.com/ML/rl/qmaze.html
This is a simulation of Bomberman using the Reinforcement Learning technique 'Q-Learning'.
Refer Wiki for documentation.
The idea is based on the the article "Deep Reinforcement Learning for Maze Solving" http://www.samyzaf.com/ML/rl/qmaze.html