Preprint · 2020 · Open access

Policy Gradient Optimization of Thompson Sampling Policies

Seungki Min, Ciamac C. Moallemi, Daniel Russo

arXiv (Cornell University) · Published 30 June 2020 · DOI 10.48550/arxiv.2006.16507

Open PDFView at the publisherCite this paper

In brief

“Policy Gradient Optimization of Thompson Sampling Policies” is a 2020 preprint by Seungki Min and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 12 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
12
Most cited in
2021 (3)
References
22
Authors
3

Abstract

We study the use of policy gradient algorithms to optimize over a class of generalized Thompson sampling policies. Our central insight is to view the posterior parameter sampled by Thompson sampling as a kind of pseudo-action. Policy gradient methods can then be tractably applied to search over a class of sampling policies, which determine a probability distribution over pseudo-actions (i.e., sampled parameters) as a function of observed data. We also propose and compare policy gradient estimators that are specialized to Bayesian bandit problems. Numerical experiments demonstrate that direct policy search on top of Thompson sampling automatically corrects for some of the algorithm's known shortcomings and offers meaningful improvements even in long horizon problems where standard Thompson sampling is extremely effective.

Cite this paper

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

APA 7

Min, S., Moallemi, C. C., & Russo, D. (2020). Policy Gradient Optimization of Thompson Sampling Policies. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2006.16507

MLA 9

Min, Seungki, et al. “Policy Gradient Optimization of Thompson Sampling Policies.” arXiv (Cornell University), 2020. https://doi.org/10.48550/arxiv.2006.16507.

Chicago

Min, Seungki, Ciamac C. Moallemi, and Daniel Russo. 2020. “Policy Gradient Optimization of Thompson Sampling Policies.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2006.16507.

Harvard

Min, S., Moallemi, C. C. and Russo, D. (2020) ‘Policy Gradient Optimization of Thompson Sampling Policies’, arXiv (Cornell University). doi:10.48550/arxiv.2006.16507.

IEEE

S. Min, C. C. Moallemi, and D. Russo, “Policy Gradient Optimization of Thompson Sampling Policies,” arXiv (Cornell University), 2020, doi: 10.48550/arxiv.2006.16507.

BibTeX

@misc{min2020policy,
  title     = {{Policy Gradient Optimization of Thompson Sampling Policies}},
  author    = {Min, Seungki and Moallemi, Ciamac C. and Russo, Daniel},
  howpublished = {arXiv (Cornell University)},
  year      = {2020},
  doi       = {10.48550/arxiv.2006.16507},
  url       = {https://doi.org/10.48550/arxiv.2006.16507}
}

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

Citations by year

YearCitationsShare of the best year
202022
202133
202211
202333
202433

Topic and keywords

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

  • Thompson sampling
  • policy gradient
  • posterior sampling
  • policy search
  • multi-armed bandits
  • long-horizon decision-making

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?

Min, S., Moallemi, C. C., & Russo, D. (2020). Policy Gradient Optimization of Thompson Sampling Policies. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2006.16507

How many times has this paper been cited?

12 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?

Seungki Min, Ciamac C. Moallemi, Daniel Russo.

What is the DOI of this paper?

10.48550/arxiv.2006.16507, permanently at https://doi.org/10.48550/arxiv.2006.16507. 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.