Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees

Item #:

068431-0780

Details

DOI: https://doi.org/10.52202/068431-0780
Author(s): Denis Belomestny, Daniele Calandriello, Pierre Ménard, Eric Moulines, Remi Munos, Alexey Naumov, Mark Rowland, Daniil Tiapkin, Michal Valko
Pages: 10737-10751 (15 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 35
Date/Location: Held 28 November - 9 December 2022, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 35
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/068431-0780
Author(s): Denis Belomestny, Daniele Calandriello, Pierre Ménard, Eric Moulines, Remi Munos, Alexey Naumov, Mark Rowland, Daniil Tiapkin, Michal Valko
Pages: 10737-10751 (15 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 35
Date/Location: Held 28 November - 9 December 2022, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 35
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)