Tadahiko Murata, Hiroshi Matsumoto. Use of Successful Policies to Relearn for Induced States of Failure in Reinforcement Learning. In Mircea Gh. Negoita, Robert J. Howlett, Lakhmi C. Jain, editors, Knowledge-Based Intelligent Information and Engineering Systems, 8th International Conference, KES 2004, Wellington, New Zealand, September 20-25, 2004. Proceedings. Part I. Volume 3213 of Lecture Notes in Computer Science, pages 1114-1120, Springer, 2004. [doi]
Abstract is missing.