Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping

Andrew Y. Ng, Daishi Harada, Stuart J. Russell. Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping. In Ivan Bratko, Saso Dzeroski, editors, Proceedings of the Sixteenth International Conference on Machine Learning (ICML 1999), Bled, Slovenia, June 27 - 30, 1999. pages 278-287, Morgan Kaufmann, 1999.

Abstract

Abstract is missing.