ADP with MCTS algorithm for Gomoku
Tang Zhentao; Zhao Dongbin; Shao Kun; Lv Le
2017-02
会议名称The 2016 IEEE Symposium Series on Computational Intelligence
会议日期6-9 Dec. 2016
会议地点Athens, Greece
摘要Inspired by the core idea of AlphaGo, we combine a neural network, which is trained by Adaptive Dynamic Programming (ADP), with Monte Carlo Tree Search (MCTS) algorithm for Gomoku. MCTS algorithm is based on Monte Carlo simulation method, which goes through lots of simulations and generates a game search tree. We rollout it and search the outcomes of the leaf nodes in the tree. As a result, we obtain the MCTS winning rate. The ADP and MCTS methods are used to estimate the winning rates respectively. We weight the two winning rates to select the action position with the maximum one. Experiment result shows that this method can effectively eliminate the neural network evaluation function's “short-sighted” defect. With our proposed method, the game's final prediction result is more accurate, and it outperforms the Gomoku with ADP algorithm.
DOI10.1109/SSCI.2016.7849371
引用统计
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/14475
专题复杂系统管理与控制国家重点实验室_深度强化学习
作者单位The State Key Laboratory of Management and Control for Complex Systems. Institute of Automation, Chinese Academy of Sciences. Beijing 100190, China
推荐引用方式
GB/T 7714
Tang Zhentao,Zhao Dongbin,Shao Kun,et al. ADP with MCTS algorithm for Gomoku[C],2017.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
07849371.pdf(866KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Tang Zhentao]的文章
[Zhao Dongbin]的文章
[Shao Kun]的文章
百度学术
百度学术中相似的文章
[Tang Zhentao]的文章
[Zhao Dongbin]的文章
[Shao Kun]的文章
必应学术
必应学术中相似的文章
[Tang Zhentao]的文章
[Zhao Dongbin]的文章
[Shao Kun]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 07849371.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。