A new accelerating algorithm for multi-agent reinforcement learning

作     者：张汝波 仲宇 顾国昌 

作者机构：Computer Science and Technology College Harbin Engineering University Harbin 150001 China Robotics Laboratory Shenyang Institute of Automation Chinese Academy of Sciences Shenyang 110015 China Computer Science and Technology College Harbin Engineering University Harbin 150001 China 

出 版 物：《Journal of Harbin Institute of Technology(New Series)》 (哈尔滨工业大学学报（英文版）)

年 卷 期：2005年第12卷第1期

页      面：48-51页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 080202[工学-机械电子工程] 081104[工学-模式识别与智能系统] 08[工学] 0804[工学-仪器科学与技术] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：SponsoredbyRoboticsLaboratory ShenyangInstituteofAutomation ChineseAcademyofSciencesFoundation(GrantNo. RL200106) 

主　　题：distributed reinforcement learning accelerating algorithm machine learning multi-agent system 

摘      要：In multi-agent systems, joint-action must be employed to achieve cooperation because the evaluation of the behavior of an agent often depends on the other agents’ behaviors. However, joint-action reinforcement learning algorithms suffer the slow convergence rate because of the enormous learning space produced by joint-action. In this article, a prediction-based reinforcement learning algorithm is presented for multi-agent cooperation tasks, which demands all agents to learn predicting the probabilities of actions that other agents may execute. A multi-robot cooperation experiment is run to test the efficacy of the new algorithm, and the experiment results show that the new algorithm can achieve the cooperation policy much faster than the primitive reinforcement learning algorithm.