[1]CAO Wei-hua,XU Ling-yun,WU Min.A double-layer decision-making model based on fuzzy Q-learning for robot soccer[J].CAAI Transactions on Intelligent Systems,2008,3(3):234-238.
Copy

A double-layer decision-making model based on fuzzy Q-learning for robot soccer

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 3 Number of periods: 2008 3 Page number: 234-238 Column: 学术论文—智能系统 Public date: 2008-06-25
Title:
A double-layer decision-making model based on fuzzy Q-learning for robot soccer
Author(s):
CAO Wei-hua; XU Ling-yun; WU Min
School of Information Science and Engineering; Central South University; Changsha 410083; China
Keywords:
robot soccer;  double-layer decision-making model;  behavior-based control system;  Q-learning
CLC:
TP18
DOI:
-
Abstract:
With the conventional trip le2layer decision2making model of soccer robots, decisions are sometimes in2 consistent, leading to weaknesses in adap tability and self2learning ability. A double2layer cooperation model for a robot soccer system based on fuzzyQ2Learning is p resented to solve these issues. Thismodel divides cooperative de2 cisions and robotmovement into two layers with their own independent functions, so that the transition from group strategy to individual behavior becomes a direct p rocess. To enhance the adap tability and self2learning capabilities of the decision2making system, the Q2learning algorithm was used in the cooperation layer to learn the op timal strat2 egy for various conditions. To speed up the convergence ofQ2learning and decrease the size of the state space, the numerous system states were mapped to seven fuzzy states in Q2learning. This avoids p roblems with Q2learning’s slow converging rate when the size of the state space is large. Thismodelwas verified on the SimuroSot Robot Soc2 cer Game p latform.
References:
[1] 赵逢达,孔令富,李贤善. 基于分层结构模型的机器人足球决策系统设计[J]哈尔滨工业大学学报, 2005,(07) .
?[2] 高阳,陈世福,陆鑫. 强化学习研究综述[J]自动化学报, 2004,(01) .
[3] 刘云江,韩光胜. 基于多智能体规划的机器人足球决策模型[J]哈尔滨工业大学学报, 2004,(07) .
[4] 郭锐,吴敏,彭军,彭姣,曹卫华. 一种新的多智能体Q学习算法[J]自动化学报, 2007,(04) .
[5] 陆永忠,柯文德. 足球机器人决策系统的设计与实现[J]计算机仿真, 2007,(09) .
?[6] ChristopherJ.C.H.Watkins,Peter Dayan. Technical Note: Q-Learning[J] Machine Learning, 1992,8, (3-4) :279~292.
[7] JohnN.Tsitsiklis. Asynchronous stochastic approximation and Q-learning[J] Machine Learning, 1994,16, (3) :185~202.
?[8] ASADA M,K ITANO H. The Robocup challenge .Robotics andAutonomous System. 1999,291, 29(1) :3-12 .
[9] Tsitsiklis,John N. Asynchronous stochastic approxi-mation and Q-learning[J] .Machine Learning, 1994,16, 16 (3) :185-202 .
Similar References:

Memo

-

Last Update: 2009-05-14

Copyright © CAAI Transactions on Intelligent Systems