Journal article · 2022 · Open access

Optimistic Posterior Sampling for Reinforcement Learning: Worst-Case Regret Bounds

Shipra Agrawal, Randy Jia

Mathematics of Operations Research, 48(1), 363–392 · Published 6 May 2022 · DOI 10.1287/moor.2022.1266

Open PDFView at the publisherCite this paper

In brief

“Optimistic Posterior Sampling for Reinforcement Learning: Worst-Case Regret Bounds” is a 2022 journal article by Shipra Agrawal and Randy Jia, published in Mathematics of Operations Research. OpenAlex counts 143 citations as of 19 November 2026, which puts it in the top 9% of works published in 2022 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
143
Most cited in
2020 (30)
Field-weighted impact
5.03
References
42
Authors
2

Abstract

We present an algorithm based on posterior sampling (aka Thompson sampling) that achieves near-optimal worst-case regret bounds when the underlying Markov decision process (MDP) is communicating with a finite, although unknown, diameter. Our main result is a high probability regret upper bound of [Formula: see text] for any communicating MDP with S states, A actions, and diameter D. Here, regret compares the total reward achieved by the algorithm to the total expected reward of an optimal infinite-horizon undiscounted average reward policy in time horizon T. This result closely matches the known lower bound of [Formula: see text]. Our techniques involve proving some novel results about the anti-concentration of Dirichlet distribution, which may be of independent interest. Funding: This work was supported in part by an NSF CAREER award [CMMI 1846792] awarded to author S. Agrawal.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Agrawal, S., & Jia, R. (2022). Optimistic Posterior Sampling for Reinforcement Learning: Worst-Case Regret Bounds. Mathematics of Operations Research, 48(1), 363–392. https://doi.org/10.1287/moor.2022.1266

MLA 9

Agrawal, Shipra, and Randy Jia. “Optimistic Posterior Sampling for Reinforcement Learning: Worst-Case Regret Bounds.” Mathematics of Operations Research, vol. 48, no. 1, 2022, pp. 363–392. https://doi.org/10.1287/moor.2022.1266.

Chicago

Agrawal, Shipra and Randy Jia. 2022. “Optimistic Posterior Sampling for Reinforcement Learning: Worst-Case Regret Bounds.” Mathematics of Operations Research 48 (1): 363–392. https://doi.org/10.1287/moor.2022.1266.

Harvard

Agrawal, S. and Jia, R. (2022) ‘Optimistic Posterior Sampling for Reinforcement Learning: Worst-Case Regret Bounds’, Mathematics of Operations Research, 48(1), pp. 363–392. doi:10.1287/moor.2022.1266.

IEEE

S. Agrawal and R. Jia, “Optimistic Posterior Sampling for Reinforcement Learning: Worst-Case Regret Bounds,” Mathematics of Operations Research, vol. 48, no. 1, pp. 363–392, 2022, doi: 10.1287/moor.2022.1266.

BibTeX

@article{agrawal2022optimistic,
  title     = {{Optimistic Posterior Sampling for Reinforcement Learning: Worst-Case Regret Bounds}},
  author    = {Agrawal, Shipra and Jia, Randy},
  journal   = {Mathematics of Operations Research},
  year      = {2022},
  volume    = {48},
  number    = {1},
  pages     = {363--392},
  doi       = {10.1287/moor.2022.1266},
  url       = {https://doi.org/10.1287/moor.2022.1266}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201733
20181111
20192727
20203030
20212222
20221010
20231717
202488
20251313
202622

Its field-weighted citation impact is 5.03: it has been cited 5.03 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Social Sciences › Decision Sciences › Management Science and Operations Research › Advanced Bandit Algorithms Research

  • posterior sampling
  • Thompson sampling
  • reinforcement learning
  • Markov decision process
  • average reward
  • Dirichlet distribution
  • anti-concentration
  • regret lower bounds

Work with this paper

Most-cited papers in Decision Sciences

All highly cited Decision Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Agrawal, S., & Jia, R. (2022). Optimistic Posterior Sampling for Reinforcement Learning: Worst-Case Regret Bounds. Mathematics of Operations Research, 48(1), 363–392. https://doi.org/10.1287/moor.2022.1266

How many times has this paper been cited?

143 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Shipra Agrawal, Randy Jia.

What is the DOI of this paper?

10.1287/moor.2022.1266, permanently at https://doi.org/10.1287/moor.2022.1266. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.