重庆理工大学学报2025，Vol.39Issue(15)：118-125,8.DOI:10.3969/j.issn.1674-8425(z).2025.08.016
引入威胁空间搜索的五子棋深度强化学习方法
Deep reinforcement learning for Gomoku with threat-space search
摘要
Abstract
Deep reinforcement learning methods integrating Monte Carlo tree search(MCTS)and deep neural networks(DNN)have become the benchmark approach for solving complex gaming problems.However,challenges such as sparse rewards and high training costs remain prominent.To address these issues,this paper proposes an improved deep reinforcement learning method for Gomoku by incorporating threat space search(TSS).First,a unified threat space search algorithm is designed.It seamlessly integrates with MCTS to mitigate the sparse reward problem.Then,a domain knowledge-based dual-layer knowledge base structure is proposed to enhance search efficiency.Next,threat-based offensive and defensive sets are incorporated as neural network input features to improve the model's perception of critical local game situations.Finally,a move filtering mechanism is developed based on threat space features to effectively reduce the action space.Experimental results demonstrate these improvements markedly enhance both the learning efficiency and competitive performance of the self-play program.关键词
蒙特卡罗树搜索/深度神经网络/威胁空间搜索/自博弈Key words
MCTS/deep neural networks/threat space search/self-play分类
信息技术与安全科学引用本文复制引用
牛学芬,王子游,陈灵,吴育华,刘雨泽,徐长明..引入威胁空间搜索的五子棋深度强化学习方法[J].重庆理工大学学报,2025,39(15):118-125,8.基金项目
河北省自然科学基金项目面上项目(F2022501015) （F2022501015）
