IDEAS home Printed from https://ideas.repec.org/a/taf/uiiexx/v57y2025i8p905-919.html
   My bibliography  Save this article

Information-directed policy sampling for episodic Bayesian Markov decision processes

Author

Listed:
  • Victoria Diaz
  • Archis Ghate

Abstract

We consider finite-stage Markov Decision Processes (MDPs) under incomplete information, where the decision-maker only knows that the true transition probability and reward matrices belong to given, finite sets. The decision-maker interacts with the system over a finite number of episodes. The first episode begins with a probabilistic belief about the true probability and reward matrices. This belief is updated at the end of each episode using observed events. The goal is to maximize the expected total reward earned over all episodes. In the resulting model-based episodic Bayesian MDP, it suffices to only consider (the known) policies that are optimal to each one of the possible probability and reward matrices. Nevertheless, the decision-maker should execute policies that provide information about the true probabilities and rewards (exploration), but also exploit this knowledge to increase rewards. We propose a framework called Information-Directed Policy Sampling (IDPS). In each episode, the decision-maker balances the exploitation-exploration trade-off by executing a randomized policy that minimizes a so-called convex information ratio. We derive a regret bound that is independent of state- and action-space cardinalities when the set of matrices is exogenously determined. Numerical experiments show IDPS outperforming a state-of-the-art approach called Posterior Sampling.

Suggested Citation

  • Victoria Diaz & Archis Ghate, 2025. "Information-directed policy sampling for episodic Bayesian Markov decision processes," IISE Transactions, Taylor & Francis Journals, vol. 57(8), pages 905-919, August.
  • Handle: RePEc:taf:uiiexx:v:57:y:2025:i:8:p:905-919
    DOI: 10.1080/24725854.2024.2392663
    as

    Download full text from publisher

    File URL: http://hdl.handle.net/10.1080/24725854.2024.2392663
    Download Restriction: Access to full text is restricted to subscribers.

    File URL: https://libkey.io/10.1080/24725854.2024.2392663?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:taf:uiiexx:v:57:y:2025:i:8:p:905-919. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Chris Longhurst (email available below). General contact details of provider: http://www.tandfonline.com/uiie .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.