XUNIK8 / Reinforcement-Learning-in-Tsumego

利用强化学习、基于蒙特卡洛树搜索的UCT算法解决围棋死活题问题。Inplement improved Reinforcement Learning and UCT algorithms (based on Monte Carlo Tree Search) on Go/Tsumego problems
13Updated last year

Related projects

Alternatives and complementary repositories for Reinforcement-Learning-in-Tsumego