Title :
Adaptive and cooperative learning for Robocup agents
Author :
Kuo, Jong Yih ; Hsieh, Frank
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Taipei Univ. of Technol., Taipei
Abstract :
In this paper, we study several adaptive learning strategies for robot agents in a Robocop game. A Q-learning based method is introduced to learning the mapping among agentpsilas actions. We apply these strategies to improve robotpsilas plan. In order to facilitate the development of shred understanding among game strategies, Pigetpsilas cognitive theory is applied to the use of cooperative learning. This paper uses a RoboCup game to explain our approach.
Keywords :
cognitive systems; cooperative systems; intelligent robots; learning systems; mobile robots; multi-robot systems; sport; Q-learning based method; Robocup agents; adaptive learning; cooperative learning; game strategies; mapping learning; robot agents; Cognition; Cognitive robotics; Computer science; Cybernetics; Intelligent agent; Intelligent robots; Machine learning; Process design; Robot sensing systems; Robotics and automation; Adaptive Learning; Cooperative Learning; Intelligent agent;
Conference_Titel :
Machine Learning and Cybernetics, 2008 International Conference on
Conference_Location :
Kunming
Print_ISBN :
978-1-4244-2095-7
Electronic_ISBN :
978-1-4244-2096-4
DOI :
10.1109/ICMLC.2008.4620945
