Preprint · 2022 · Open access

A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning

Christoph Dann, Mehryar Mohri, Tong Zhang, Julian Zimmert

arXiv (Cornell University), 34 · Published 23 August 2022 · DOI 10.48550/arxiv.2208.10904

Open PDFView at the publisherCite this paper

In brief

“A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning” is a 2022 preprint by Christoph Dann and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 46 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
46
Most cited in
2023 (16)
References
28
Authors
4

Abstract

Thompson Sampling is one of the most effective methods for contextual bandits and has been generalized to posterior sampling for certain MDP settings. However, existing posterior sampling methods for reinforcement learning are limited by being model-based or lack worst-case theoretical guarantees beyond linear MDPs. This paper proposes a new model-free formulation of posterior sampling that applies to more general episodic reinforcement learning problems with theoretical guarantees. We introduce novel proof techniques to show that under suitable conditions, the worst-case regret of our posterior sampling method matches the best known results of optimization based methods. In the linear MDP setting with dimension, the regret of our algorithm scales linearly with the dimension as compared to a quadratic dependence of the existing posterior sampling-based exploration algorithms.

Cite this paper

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

APA 7

Dann, C., Mohri, M., Zhang, T., & Zimmert, J. (2022). A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning. arXiv (Cornell University), 34. https://doi.org/10.48550/arxiv.2208.10904

MLA 9

Dann, Christoph, et al. “A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning.” arXiv (Cornell University), vol. 34, 2022. https://doi.org/10.48550/arxiv.2208.10904.

Chicago

Dann, Christoph, Mehryar Mohri, Tong Zhang, and Julian Zimmert. 2022. “A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning.” arXiv (Cornell University) 34. https://doi.org/10.48550/arxiv.2208.10904.

Harvard

Dann, C. et al. (2022) ‘A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning’, arXiv (Cornell University), 34. doi:10.48550/arxiv.2208.10904.

IEEE

C. Dann, M. Mohri, T. Zhang, and J. Zimmert, “A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning,” arXiv (Cornell University), vol. 34, 2022, doi: 10.48550/arxiv.2208.10904.

BibTeX

@misc{dann2022provably,
  title     = {{A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning}},
  author    = {Dann, Christoph and Mohri, Mehryar and Zhang, Tong and Zimmert, Julian},
  howpublished = {arXiv (Cornell University)},
  year      = {2022},
  volume    = {34},
  doi       = {10.48550/arxiv.2208.10904},
  url       = {https://doi.org/10.48550/arxiv.2208.10904}
}

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

Citations by year

YearCitationsShare of the best year
202011
202111
202277
20231616
202488
202577
202666

Topic and keywords

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

  • posterior sampling
  • episodic reinforcement learning
  • model-free reinforcement learning
  • Thompson sampling
  • regret bounds
  • exploration
  • contextual bandits
  • worst-case regret

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?

Dann, C., Mohri, M., Zhang, T., & Zimmert, J. (2022). A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning. arXiv (Cornell University), 34. https://doi.org/10.48550/arxiv.2208.10904

How many times has this paper been cited?

46 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?

Christoph Dann, Mehryar Mohri, Tong Zhang, Julian Zimmert.

What is the DOI of this paper?

10.48550/arxiv.2208.10904, permanently at https://doi.org/10.48550/arxiv.2208.10904. 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.