Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration

Priyank Agrawal, Jinglin Chen, Nan Jiang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper studies regret minimization with randomized value functions in reinforcement learning. In tabular finite-horizon Markov Decision Processes, we introduce a clipping variant of one classical Thompson Sampling (TS)-like algorithm, randomized least-squares value iteration (RLSVI). Our Õ(H2S√AT) high-probability worst-case regret bound improves the previous sharpest worst-case regret bounds for RLSVI and matches the existing state-of-the-art worst-case TS-based regret bounds.

Original languageEnglish (US)
Title of host publication35th AAAI Conference on Artificial Intelligence, AAAI 2021
PublisherAssociation for the Advancement of Artificial Intelligence
Pages6566-6573
Number of pages8
ISBN (Electronic)9781713835974
StatePublished - 2021
Event35th AAAI Conference on Artificial Intelligence, AAAI 2021 - Virtual, Online
Duration: Feb 2 2021Feb 9 2021

Publication series

Name35th AAAI Conference on Artificial Intelligence, AAAI 2021
Volume8A

Conference

Conference35th AAAI Conference on Artificial Intelligence, AAAI 2021
CityVirtual, Online
Period2/2/212/9/21

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration'. Together they form a unique fingerprint.

Cite this