A Two-Timescale Simulation-Based Gradient Algorithm for Weighted Cost Markov Decision Processes

Ying He 0014, Michael C. Fu 0001, Steven I. Marcus. A Two-Timescale Simulation-Based Gradient Algorithm for Weighted Cost Markov Decision Processes. In 44th IEEE IEEE Conference on Decision and Control and 8th European Control Conference Control, CDC/ECC 2005, Seville, Spain, 12-15 December, 2005. pages 8022-8027, IEEE, 2005. [doi]

Abstract

Abstract is missing.