Rates of Convergence of Performance Gradient Estimates Using Function Approximation and Bias in Reinforcement Learning

Gregory Z. Grudic, Lyle H. Ungar. Rates of Convergence of Performance Gradient Estimates Using Function Approximation and Bias in Reinforcement Learning. In Thomas G. Dietterich, Suzanna Becker, Zoubin Ghahramani, editors, Advances in Neural Information Processing Systems 14 [Neural Information Processing Systems: Natural and Synthetic, NIPS 2001, December 3-8, 2001, Vancouver, British Columbia, Canada]. pages 1515-1522, MIT Press, 2001. [doi]

Abstract

Abstract is missing.