[1]ZHANG Xiaochuan,TANG Yan,LIANG Ningning.A 9×9 Go computer game system using temporal difference[J].CAAI Transactions on Intelligent Systems,2012,7(3):278-282.
Copy

A 9×9 Go computer game system using temporal difference

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 7 Number of periods: 2012 3 Page number: 278-282 Column: 学术论文—智能系统 Public date: 2012-06-25
Title:
A 9×9 Go computer game system using temporal difference
Author(s):
ZHANG Xiaochuan;  TANG Yan;  LIANG Ningning
College of Computer Science and Engineering, Chongqing University of Technology, Chongqing 400054, China
Keywords:
computer game;  9×9 Go;  Go computer game;  temporal difference
CLC:
TP31
DOI:
-
Abstract:
Computer Go is an important branch of computer games and presents great challenges to computer game researchers due to its need for huge game space. Presently, the static evaluation method and the MonteCarlo tree search method are widely used in Go computer games. In this paper, a temporal difference algorithm was introduced to the 9×9 Go computer game system which gave it selflearning capability, thereby improving the game levels as a result of the continuous training. Through playing chess with a system which adopts an αβ algorithm, the new method was proven to be effective.
References:
［1］张聪品，刘春红，徐久成．博弈树启发式搜索的αβ剪枝技术研究［J］．计算机工程与应用, 2008, 44(16): 5455, 97.
 ZHANG Congpin, LIU Chunhong, XU Jiucheng. Research on alphabeta pruning of heuristic search in gameplaying tree［J］. Computer Engineering and Applications, 2008,44(16): 5455, 97.
［2］刘知青，李文峰．现代计算机围棋基础［M］．北京：北京邮电大学出版社, 2011: 6380.
［3］GELLY S, WANG Yizao, MUNOS R, et al. Modification of UCT with patterns in MonteCarlo Go［R/OL］. ［20111015］. http://219.142.86.87/paper/RR6062.pdf.
［4］GELLY S, WANG Yizao. Exploration exploitation in Go: UCT for MonteCarlo Go［C/OL］. ［20111015］. http://wenku.baidu.com/view/66c2edd6b9f3f90f76c61bc0.html.
［5］张汝波，周宁，顾国昌，等．基于强化学习的智能机器人避碰方法研究［J］．机器人, 1995, 21 (3): 204209.
ZHANG Rubo, ZHOU Ning, GU Guochang, et al. Reinforcement learning based obstacle avoidance learning for intelligent robot［J］. Robot, 1995, 21 (3): 204209.
［6］沈晶，顾国昌，刘海波．基于免疫聚类的自动分层强化学习方法研究［J］．哈尔滨工程大学学报, 2007, 28(4): 423428.
SHEN Jing, GU Guochang, LIU Haibo. Hierarchical reinforcement learning with an automatically generated hierarchy based on immune clustering［J］. Journal of Harbin Engineering University, 2007, 28(4): 423428.
［7］BAE J, CHHATBAR P, FRANCIS J T, et al. Reinforcement learning via kernel temporal difference［C］//Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Boston, USA， 2011: 56625665.
［8］SUTTON R S. Learning to predict by the methods of temporal difference［J］. Machine Learning, 1988, 3(1): 944.
［9］KAELBLING L P, LITTMAN M L, MOORE A W. Reinforcement learning: a survey［J］. Journal of Artificial Intelligence Research, 1996, 4: 237285.
［10］阿培丁．机器学习导论［M］．范明，昝红英，牛常勇，译．北京：机械工业出版社, 2009: 372390.
［11］SUTTON R S, BARTO A G. Reinforcement learning: an introduction［M］. Cambridge, USA: The MIT Press, 1997.
［12］聂卫平，冯大树．聂卫平围棋道场［M］．北京：北京体育大学出版社, 2004.
［13］徐长明，马宗民，徐心和，等．面向机器博弈的即时差分学习研究［J］．计算机科学, 2010, 37(8): 219224.
XU Changming, MA Zongmin, XU Xinhe, et al. Study of temporal difference learning in computer games［J］. Computer Science, 2010, 37(8): 219224.
Similar References:

Memo

-

Last Update: 2012-09-05

Copyright © CAAI Transactions on Intelligent Systems