First-Order Bayesian Regret Analysis of Thompson Sampling

v1v2v3 (latest)

First-Order Bayesian Regret Analysis of Thompson Sampling

IEEE Transactions on Information Theory (IEEE Trans. Inf. Theory), 2019

2 February 2019

Sébastien Bubeck

ArXiv (abs)PDF HTML

Papers citing "First-Order Bayesian Regret Analysis of Thompson Sampling"

17 / 17 papers shown

Title
Sparse Optimistic Information Directed Sampling Ludovic Schwartz Hamish Flynn Gergely Neu 44 0 0 28 Oct 2025
Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts Benjamin Schiffer Mark Sellke 171 0 0 02 Jun 2025
Policy Gradient with Active Importance Sampling Matteo Papini Giorgio Manganini Alberto Maria Metelli Marcello Restelli OffRL 155 4 0 09 May 2024
Optimistic Information Directed Sampling Gergely Neu Matteo Papini Ludovic Schwartz 249 3 0 23 Feb 2024
Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2023 Ahmadreza Moradipari M. Pedramfar Modjtaba Shokrian Zini Vaneet Aggarwal 261 6 0 30 Oct 2023
Incentivizing Exploration with Linear Contexts and Combinatorial ActionsInternational Conference on Machine Learning (ICML), 2023 Mark Sellke 219 4 0 03 Jun 2023
The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2023 Kaiwen Wang Kevin Zhou Runzhe Wu Nathan Kallus Wen Sun OffRL 410 23 0 25 May 2023
Regret Bounds for Information-Directed Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2022 Botao Hao Tor Lattimore OffRL 234 23 0 09 Jun 2022
Deciding What to Model: Value-Equivalent Sampling for Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2022 Dilip Arumugam Benjamin Van Roy OffRL 226 18 0 04 Jun 2022
Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual BanditsNeural Information Processing Systems (NeurIPS), 2022 Gergely Neu Julia Olkhovskaya Matteo Papini Ludovic Schwartz 272 20 0 27 May 2022
Gaussian Imagination in Bandit Learning Yueyang Liu Adithya M. Devraj Benjamin Van Roy Kuang Xu 184 7 0 06 Jan 2022
First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation ApproachInternational Conference on Machine Learning (ICML), 2021 Andrew Wagenmaker Yifang Chen Max Simchowitz S. Du Kevin Jamieson 271 47 0 07 Dec 2021
The Value of Information When Deciding What to Learn Dilip Arumugam Benjamin Van Roy 138 16 0 26 Oct 2021
Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination Dylan J. Foster A. Krishnamurthy 167 52 0 05 Jul 2021
Information Directed Sampling for Sparse Linear BanditsNeural Information Processing Systems (NeurIPS), 2021 Botao Hao Tor Lattimore Wei Deng 192 21 0 29 May 2021
Reinforcement Learning, Bit by Bit Xiuyuan Lu Benjamin Van Roy Vikranth Dwaracherla M. Ibrahimi Ian Osband Zheng Wen 422 76 0 06 Mar 2021
Mirror Descent and the Information RatioAnnual Conference Computational Learning Theory (COLT), 2020 Tor Lattimore András Gyorgy 210 44 0 25 Sep 2020