When Policies Can Be Trusted: Analyzing a Criteria to Identify Optimal Policies in MDPs with Unknown Model Parameters

Emma Brunskill. When Policies Can Be Trusted: Analyzing a Criteria to Identify Optimal Policies in MDPs with Unknown Model Parameters. In Ronen I. Brafman, Hector Geffner, Jörg Hoffmann, Henry A. Kautz, editors, Proceedings of the 29th International Conference on Automated Planning and Scheduling, ICAPS 2010, Toronto, Ontario, Canada, May 12-16, 2010. pages 218-221, AAAI, 2010. [doi]

Abstract

Abstract is missing.