基于强化学习的苏拉卡尔塔博弈算法

An reinforcement based game algorithm of Surakarta

本文探讨了基于蒙特卡洛方法的强化学习博弈程序的原理,基于该原理结合BP算法设计了一个进行自学习的苏拉卡尔塔博弈程序。实验证明,该方法能让智能体不断的学习提高棋力,避免了繁琐的手工构建静态评估函数过程。

The author discusses the principle of MCTS-based reinforcement learning.Based on this principle,BP algorithm is combined,we design a self-learning game playing program of Surakarta.The experiment shows that the methods can improve the performance of the agent,avoiding design static evaluating function by hand.