Donald F. Beal. TD (mu): A Modificaiton of TD (lambda) That Enables a Program to Learn Weights for Good Play Even if It Observes Only Bad Play. In H. John Caulfield, Shu-Heng Chen, Heng-Da Cheng, Richard J. Duro, Vasant Honavar, Etienne E. Kerre, Mi Lu, Manuel Grana Romay, Timothy K. Shih, Dan Ventura, Paul P. Wang, Yuanyuan Yang, editors, Proceedings of the 6th Joint Conference on Information Science, March 8-13, 2002, Research Triangle Park, North Carolina, USA. pages 473-476, JCIS / Association for Intelligent Machinery, Inc., 2002.
Abstract is missing.