A Bayesian sampling approach to exploration in reinforcement learning英文版.pdfVIP

A Bayesian Sampling Approach to Exploration in Reinforcement Learning John Asmuth† Lihong Li† Michael L. Littman† Ali Nouri† David Wingate‡ †Department of Computer Science ‡Computational Cognitive Science Group Rutgers University Massachusetts Institute of Technology Piscataway, NJ 08854 Cambridge, MA 02143 Abstract