Q_learning_demo

Dependencies

Python 2.7
tkinter

Human play

python human_player.py --difficulty 0|1|2

AI play

python ai_player.py --difficulty 0|1|2 --max-iteration 20

Branch q-learng-study

Branch q-learning-study is for Q-learning teaching purpose. The key function are removed

Credits

This code is modified from https://github.com/llSourcell/q_learning_demo.git. I wrap the agent.py as with better api that Q-learning algorithm can call it easily