ADAPTIVE AND COOPERATIVE LEARNING FOR ROBOCUP AGENTS

摘要：

In this paper, we study several adaptive learning strategies for robot agents in a Kobocop game. A Q-learning based method is introduced to learning the mapping among agents actions. We apply these strategies to improve robots plan. In order to facilitate the development of shred understanding among game strategies, Pigets cognitive theory is applied to the use of cooperative learning. This paper uses a RoboCup game to explain our approach.

关键词： Intelligent agent Adaptive Learning Cooperative Learning

作者: JONG YIH KUO FRANK HSIEH

作者单位: Department of Computer Science and Information Engineering National Taipei University of Technology

会议类型: 国际会议

会议名称: 2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

会议地点: 昆明

会议语种:英文

页码: 3125-3131

在线出版日期: 2008-07-12（万方平台首次上网日期，不代表论文的发表时间）