Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs

Max Simchowitz, Kevin G. Jamieson. Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs. In Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alché-Buc, Edward A. Fox, Roman Garnett, editors, Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8-14 December 2019, Vancouver, BC, Canada. pages 1151-1160, 2019. [doi]

Authors

Max Simchowitz

This author has not been identified. Look up 'Max Simchowitz' in Google

Kevin G. Jamieson

This author has not been identified. Look up 'Kevin G. Jamieson' in Google