IDEAS home Printed from https://ideas.repec.org/a/spr/annopr/v317y2022i2d10.1007_s10479-015-1965-7.html
   My bibliography  Save this article

Robust control of the multi-armed bandit problem

Author

Listed:
  • Felipe Caro

    (UCLA Anderson School of Management)

  • Aparupa Das Gupta

    (UCLA Anderson School of Management)

Abstract

We study a robust model of the multi-armed bandit (MAB) problem in which the transition probabilities are ambiguous and belong to subsets of the probability simplex. We first show that for each arm there exists a robust counterpart of the Gittins index that is the solution to a robust optimal stopping-time problem and can be computed effectively with an equivalent restart problem. We then characterize the optimal policy of the robust MAB as a project-by-project retirement policy but we show that arms become dependent so the policy based on the robust Gittins index is not optimal. For a project selection problem, we show that the robust Gittins index policy is near optimal but its implementation requires more computational effort than solving a non-robust MAB problem. Hence, we propose a Lagrangian index policy that requires the same computational effort as evaluating the indices of a non-robust MAB and is within 1 % of the optimum in the robust project selection problem.

Suggested Citation

  • Felipe Caro & Aparupa Das Gupta, 2022. "Robust control of the multi-armed bandit problem," Annals of Operations Research, Springer, vol. 317(2), pages 461-480, October.
    • Handle: RePEc:spr:annopr:v:317:y:2022:i:2:d:10.1007_s10479-015-1965-7
    DOI: 10.1007/s10479-015-1965-7
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s10479-015-1965-7
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.
    File URL: https://libkey.io/10.1007/s10479-015-1965-7?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.

    References listed on IDEAS

    as
    1. Roberts, Kevin & Weitzman, Martin L, 1981. "Funding Criteria for Research, Development, and Exploration Projects," Econometrica, Econometric Society, vol. 49(5), pages 1261-1288, September.
    2. Besbes, Omar & Gur, Yonatan & Zeevi, Assaf, 2014. "Optimal Exploration-Exploitation in a Multi-armed-Bandit Problem with Non-stationary Rewards," Research Papers 3147, Stanford University, Graduate School of Business.
    3. Dimitrov, Nedialko B. & Dimitrov, Stanko & Chukova, Stefanka, 2014. "Robust decomposable Markov decision processes motivated by allocating school budgets," European Journal of Operational Research, Elsevier, vol. 239(1), pages 199-213.
    4. Eric Denardo & Eugene Feinberg & Uriel Rothblum, 2013. "The multi-armed bandit, with constraints," Annals of Operations Research, Springer, vol. 208(1), pages 37-62, September.
    5. Erick Delage & Shie Mannor, 2010. "Percentile Optimization for Markov Decision Processes with Parameter Uncertainty," Operations Research, INFORMS, vol. 58(1), pages 203-213, February.
    6. Wolfram Wiesemann & Daniel Kuhn & Berç Rustem, 2013. "Robust Markov Decision Processes," Mathematics of Operations Research, INFORMS, vol. 38(1), pages 153-183, February.
    7. Chelsea C. White & Hany K. Eldeib, 1994. "Markov Decision Processes with Imprecise Transition Probabilities," Operations Research, INFORMS, vol. 42(4), pages 739-749, August.
    8. Apostolos N. Burnetas & Michael N. Katehakis, 1997. "Optimal Adaptive Policies for Markov Decision Processes," Mathematics of Operations Research, INFORMS, vol. 22(1), pages 222-255, February.
    9. Garud N. Iyengar, 2005. "Robust Dynamic Programming," Mathematics of Operations Research, INFORMS, vol. 30(2), pages 257-280, May.
    10. Michael N. Katehakis & Arthur F. Veinott, 1987. "The Multi-Armed Bandit Problem: Decomposition and Computation," Mathematics of Operations Research, INFORMS, vol. 12(2), pages 262-268, May.
    11. Jay K. Satia & Roy E. Lave, 1973. "Markovian Decision Processes with Uncertain Transition Probabilities," Operations Research, INFORMS, vol. 21(3), pages 728-740, June.
    12. Arnab Nilim & Laurent El Ghaoui, 2005. "Robust Control of Markov Decision Processes with Uncertain Transition Matrices," Operations Research, INFORMS, vol. 53(5), pages 780-798, October.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Andrew J. Keith & Darryl K. Ahner, 2021. "A survey of decision making and optimization under uncertainty," Annals of Operations Research, Springer, vol. 300(2), pages 319-353, May.
    2. V Varagapriya & Vikas Vikram Singh & Abdel Lisser, 2023. "Joint chance-constrained Markov decision processes," Annals of Operations Research, Springer, vol. 322(2), pages 1013-1035, March.
    3. Zhu, Zhicheng & Xiang, Yisha & Zhao, Ming & Shi, Yue, 2023. "Data-driven remanufacturing planning with parameter uncertainty," European Journal of Operational Research, Elsevier, vol. 309(1), pages 102-116.
    4. Zeynep Turgay & Fikri Karaesmen & Egemen Lerzan Örmeci, 2018. "Structural properties of a class of robust inventory and queueing control problems," Naval Research Logistics (NRL), John Wiley & Sons, vol. 65(8), pages 699-716, December.
    5. David L. Kaufman & Andrew J. Schaefer, 2013. "Robust Modified Policy Iteration," INFORMS Journal on Computing, INFORMS, vol. 25(3), pages 396-410, August.
    6. Wolfram Wiesemann & Daniel Kuhn & Berç Rustem, 2013. "Robust Markov Decision Processes," Mathematics of Operations Research, INFORMS, vol. 38(1), pages 153-183, February.
    7. Peter Buchholz & Dimitri Scheftelowitsch, 2019. "Computation of weighted sums of rewards for concurrent MDPs," Mathematical Methods of Operations Research, Springer;Gesellschaft für Operations Research (GOR);Nederlands Genootschap voor Besliskunde (NGB), vol. 89(1), pages 1-42, February.
    8. Shie Mannor & Ofir Mebel & Huan Xu, 2016. "Robust MDPs with k -Rectangular Uncertainty," Mathematics of Operations Research, INFORMS, vol. 41(4), pages 1484-1509, November.
    9. Arthur Flajolet & Sébastien Blandin & Patrick Jaillet, 2018. "Robust Adaptive Routing Under Uncertainty," Operations Research, INFORMS, vol. 66(1), pages 210-229, January.
    10. Saghafian, Soroush, 2018. "Ambiguous partially observable Markov decision processes: Structural results and applications," Journal of Economic Theory, Elsevier, vol. 178(C), pages 1-35.
    11. Bren, Austin & Saghafian, Soroush, 2018. "Data-Driven Percentile Optimization for Multi-Class Queueing Systems with Model Ambiguity: Theory and Application," Working Paper Series rwp18-008, Harvard University, John F. Kennedy School of Government.
    12. Bakker, Hannah & Dunke, Fabian & Nickel, Stefan, 2020. "A structuring review on multi-stage optimization under uncertainty: Aligning concepts from theory and practice," Omega, Elsevier, vol. 96(C).
    13. Maximilian Blesch & Philipp Eisenhauer, 2023. "Robust Decision-Making under Risk and Ambiguity," Rationality and Competition Discussion Paper Series 463, CRC TRR 190 Rationality and Competition.
    14. Boloori, Alireza & Saghafian, Soroush & Chakkera, Harini A. A. & Cook, Curtiss B., 2017. "Data-Driven Management of Post-transplant Medications: An APOMDP Approach," Working Paper Series rwp17-036, Harvard University, John F. Kennedy School of Government.
    15. Maximilian Blesch & Philipp Eisenhauer, 2021. "Robust Decision-Making Under Risk and Ambiguity," ECONtribute Discussion Papers Series 104, University of Bonn and University of Cologne, Germany.
    16. Erim Kardeş & Fernando Ordóñez & Randolph W. Hall, 2011. "Discounted Robust Stochastic Games and an Application to Queueing Control," Operations Research, INFORMS, vol. 59(2), pages 365-382, April.
    17. Maximilian Blesch & Philipp Eisenhauer, 2021. "Robust decision-making under risk and ambiguity," Papers 2104.12573, arXiv.org, revised Oct 2021.
    18. Rasouli, Mohammad & Saghafian, Soroush, 2018. "Robust Partially Observable Markov Decision Processes," Working Paper Series rwp18-027, Harvard University, John F. Kennedy School of Government.
    19. Wolfram Wiesemann & Daniel Kuhn & Berç Rustem, 2010. "Robust Markov Decision Processes," Working Papers 034, COMISEF.
    20. Erick Delage & Shie Mannor, 2010. "Percentile Optimization for Markov Decision Processes with Parameter Uncertainty," Operations Research, INFORMS, vol. 58(1), pages 203-213, February.

    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:spr:annopr:v:317:y:2022:i:2:d:10.1007_s10479-015-1965-7. 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.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with 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: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    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.