Tic-tac-toe Bot based on Q-learning

Q-learning is a model-free reinforcement learning technique. Specifically, Q-learning can be used to find an optimal action-selection policy for any given (finite) Markov decision process (MDP).

If you find bugs or have suggestions, feel free to email me at aiba.prenov@gmail.com

Installation

python 3 required

git clone https://github.com/aibaq/tic_tac_q.git

python main.py or python3 main.py