|
|||
Gradient-Based Learning Updates Improve XCS Performance in Multistep ProblemsMartin V. Butz, David E. Goldberg, and Pier Luca Lanzi Illinois Genetic Algorithms Laboratory (IlliGAL), University of Illinois at Urbana-Champaign, Urbana, IL, 61801butz@illigal.ge.uiuc.edu deg@illigal.ge.uiuc.edu lanzi@illigal.ge.uiuc.edu Abstract. This paper introduces a gradient-based reward prediction update mechanism to the XCS classifier system as applied in neural-network type learning and function approximation mechanisms. A strong relation of XCS to tabular reinforcement learning and more importantly to neural-based reinforcement learning techniques is drawn. The resulting gradient-based XCS system learns more stable and reliable in previously investigated hard multistep problems. While the investigations are limited to the binary XCS classifier system, the applied gradient-based update mechanism appears also suitable for the real-valued XCS and other learning classifier systems. LNCS 3103, p. 751 ff. lncs@springer.de
|