ADP with MCTS algorithm for Gomoku

doi:10.1109/SSCI.2016.7849371

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 深度强化学习

	ADP with MCTS algorithm for Gomoku
	Tang Zhentao; Zhao Dongbin; Shao Kun; Lv Le
	2017-02
会议日期	6-9 Dec. 2016
会议地点	Athens, Greece
DOI	10.1109/SSCI.2016.7849371
英文摘要	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.
内容类型	会议论文
源URL	[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]. 见:. Athens, Greece. 6-9 Dec. 2016.