Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning

Authors: Ahmadreza Moradipari, Mohammad Pedramfar, Modjtaba Shokrian Zini, Vaneet Aggarwal

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we prove the first Bayesian regret bounds for Thompson Sampling in reinforcement learning in a multitude of settings.
Researcher Affiliation Collaboration Toyota Motor North America, Info Tech Labs, Mountain View, CA, USA, ahmadreza.moradipari@toyota.com Purdue University, West Lafayette, IN, USA, mpedramf@purdue.edu modjtaba.shokrianzini@gmail.com Purdue University, West Lafayette, IN, USA, vaneet@purdue.edu
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described, nor does it explicitly state that code is being released or made available.
Open Datasets No The paper does not provide concrete access information for a publicly available or open dataset, as it is a theoretical paper and does not report on experiments.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce data partitioning, as it is a theoretical paper and does not report on experiments.
Hardware Specification No The paper does not provide specific hardware details used for running experiments, as it is a theoretical paper and does not report on experimental setups.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate experiments, as it is a theoretical paper.
Experiment Setup No The paper does not contain specific experimental setup details (concrete hyperparameter values, training configurations, or system-level settings) in the main text, as it is a theoretical paper and does not describe experiments.