The complexity of Policy Iteration is exponential for discounted Markov Decision Processes

Romain Hollanders, Jean-Charles Delvenne, Raphael M. Jungers. The complexity of Policy Iteration is exponential for discounted Markov Decision Processes. In Proceedings of the 51th IEEE Conference on Decision and Control, CDC 2012, December 10-13, 2012, Maui, HI, USA. pages 5997-6002, IEEE, 2012. [doi]

Abstract

Abstract is missing.