Q-learning算法及其在囚徒困境问题中的实现

Q-learning Algorithm and Its Usage in Prisoner's Dilemma

Ｑ－ｌｅａｒｎｉｎｇ是一种优良的强化学习算法。该文首先阐述了Ｑ－ｌｅａｒｎｉｎｇ的基本学习机制，然后以囚徒困境问题为背景，分析、对比Ｔ Ｑ－ｌｅａｒｎｉｎｇ算法与ＴＦＴ算法，验证了 Ｑ－ｌｅａｒｎｉｎｇ算法的优良特性。

Q-learning is an algorithm of Reinforcement learning algorithm.In this paper,We elaborate the learning method of Q-learning algorithm simply,use it in prisoner's dilemma game and compare it with TFT to show its good character.