首页 | 本学科首页   官方微博 | 高级检索  
     

一种基于Agent团队的强化学习模型与应用研究
引用本文:蔡庆生,张波.一种基于Agent团队的强化学习模型与应用研究[J].计算机研究与发展,2000,37(9):1087-1093.
作者姓名:蔡庆生  张波
作者单位:中国科学技术大学计算机科学与技术系,合肥,230027
基金项目:国家自然科学基金资助!(项目编号 69675 0 16)
摘    要:多Agent学习是近年来受到较多关注的研究方向,以单Agent强化Q-learning算法为基础,提出了一种基于Agent团队的强化学习模,这个模型的最大特点是引入主导Agent作为团队学习的主角,并通过主导Agent的角色变换实现整个团队的学习。结合仿真机器人足球领域,设计了具体的应用模型,在几个方面对Q-learning进行扩充,并进行了实验,在仿真机器人足球领域的成功应用表明了这个模型的有效

关 键 词:Agent团队  机器人足球  强化学习模型  人工智能

AN AGENT TEAM BASED REINFORCEMENT LEARNING MODEL AND ITS APPLICATION
CAI Qing-Sheng,ZHANG Bo.AN AGENT TEAM BASED REINFORCEMENT LEARNING MODEL AND ITS APPLICATION[J].Journal of Computer Research and Development,2000,37(9):1087-1093.
Authors:CAI Qing-Sheng  ZHANG Bo
Abstract:Multi agent learning has attracted increasing attention in recent years. In this paper, a novel model for reinforcement learning based on agent team is proposed. Its basis is Q learning, a single agent reinforcement learning algorithm. The most significant characteristic of the model is the introduction of the active agent, the major role in team learning. By switching the active agent, team learning is achieved. A model in robotic soccer domain is implemented by extending the Q learing algorithm, and some positive results are obtained in experiments. Success in robotic soccer domain shows the effectiveness of the model.
Keywords:agent team  reinforcement learning  robotic soccer
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号