Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs

Ambuj Tewari, Peter L. Bartlett. Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs. In John C. Platt, Daphne Koller, Yoram Singer, Sam T. Roweis, editors, Advances in Neural Information Processing Systems 20, Proceedings of the Twenty-First Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 3-6, 2007. pages 1505-1512, MIT Press, 2007. [doi]

Abstract

Abstract is missing.