文档a reinforcement learning adaptive fuzzy controller for differential games_jrlib.com.pdf

J Intell Robot Syst (2010) 59:3–30 DOI 10.1007/s10846-009-9380-4 A Reinforcement Learning Adaptive Fuzzy Controller for Differential Games Sidney N. Givigi Jr. · Howard M. Schwartz · Xiaosong Lu Received: 4 June 2008 / Accepted: 28 September 2009 / Published online: 23 October 2009 © Springer Science + Business Media B.V. 2009 Abstract In this paper we develop a reinforcement fuzzy learning scheme for robots playing a differential game. Differential games are games played in continuous time, with continuous states and actions. Fuzzy controllers are used to approximate the calculation of future reinforcements of the game due to actions taken at a specific time. If an immediate reinforcement reward function is defined, we may use a fuzzy system to tell what is the predicted reinforcement in a specified time ahead. This reinforcement is then used to adapt a fuzzy controller that stores the experience accumulated by the player. Simulations of a modified two car game are provided in order to show the potentiality of the technique. Experiments are performed in order to validate the method. Finally, it should be noted that although the game used as an example involves only two players, the technique may also be used in a multi-game environment. Keywords Differential games · Learning · Pursuer-evader games · Intelligent systems · Reinforcement learning ·Fuzzy control S. N. Givigi Jr. ( ) B Department of Electrical and Computer Engineering, Royal Military College of Canada, P.O. Box 17000 Station Forces, Kingston, Ontario K7K 7B4, Canada e-mail: Sidney.Givigi@rmc.ca H. M. Schwartz · X. Lu Systems and Computer Engineering, Carleton University, 1125 Colonel By Drive, Ottawa, Ontario K1S 5B6, Canada H. M. Schwartz e-mail: schwartz@sce.carleton.ca X. Lu e-mail: luxiaos@sce.carleton.ca 4 J Intell Robot Syst (2010) 59:3–30 1 Introduction