[go: up one dir, main page]
IDEAS home Printed from https://ideas.repec.org/p/nbr/nberwo/32424.html
   My bibliography  Save this paper

Disentangling Exploration from Exploitation

Author

Listed:
  • Alessandro Lizzeri
  • Eran Shmaya
  • Leeat Yariv
Abstract
Starting from Robbins (1952), the literature on experimentation via multi-armed bandits has wed exploration and exploitation. Nonetheless, in many applications, agents' exploration and exploitation need not be intertwined: a policymaker may assess new policies different than the status quo; an investor may evaluate projects outside her portfolio. We characterize the optimal experimentation policy when exploration and exploitation are disentangled in the case of Poisson bandits, allowing for general news structures. The optimal policy features complete learning asymptotically, exhibits lots of persistence, but cannot be identified by an index à la Gittins. Disentanglement is particularly valuable for intermediate parameter values.

Suggested Citation

  • Alessandro Lizzeri & Eran Shmaya & Leeat Yariv, 2024. "Disentangling Exploration from Exploitation," NBER Working Papers 32424, National Bureau of Economic Research, Inc.
    • Handle: RePEc:nbr:nberwo:32424
    Note: EH IO LE LS ME POL
    as

    Download full text from publisher

    File URL: http://www.nber.org/papers/w32424.pdf
    Download Restriction: Access to the full text is generally limited to series subscribers, however if the top level domain of the client browser is in a developing country or transition economy free access is provided. More information about subscriptions and free access is available at http://www.nber.org/wwphelp.html. Free access is also available to older working papers.
    ---><---

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

    Other versions of this item:

    References listed on IDEAS

    as
    1. Janet M. Currie & W. Bentley MacLeod, 2020. "Understanding Doctor Decision Making: The Case of Depression Treatment," Econometrica, Econometric Society, vol. 88(3), pages 847-878, May.
    2. Rothschild, Michael, 1974. "A two-armed bandit theory of market pricing," Journal of Economic Theory, Elsevier, vol. 9(2), pages 185-202, October.
    3. Miller, Robert A, 1984. "Job Matching and Occupational Choice," Journal of Political Economy, University of Chicago Press, vol. 92(6), pages 1086-1120, December.
    4. Yeon-Koo Che & Konrad Mierendorff, 2019. "Optimal Dynamic Allocation of Attention," American Economic Review, American Economic Association, vol. 109(8), pages 2993-3029, August.
    5. Johannes Hörner & Larry Samuelson, 2013. "Incentives for experimenting agents," RAND Journal of Economics, RAND Corporation, vol. 44(4), pages 632-663, December.
    6. , & ,, 2010. "Strategic experimentation with Poisson bandits," Theoretical Economics, Econometric Society, vol. 5(2), May.
    7. Godfrey Keller & Sven Rady & Martin Cripps, 2005. "Strategic Experimentation with Exponential Bandits," Econometrica, Econometric Society, vol. 73(1), pages 39-68, January.
    8. Ettore Damiano & Hao Li & Wing Suen, 2020. "Learning While Experimenting," The Economic Journal, Royal Economic Society, vol. 130(625), pages 65-92.
    9. Jovanovic, Boyan, 1979. "Job Matching and the Theory of Turnover," Journal of Political Economy, University of Chicago Press, vol. 87(5), pages 972-990, October.
    10. repec:cwl:cwldpp:1726rrr is not listed on IDEAS
    11. repec:cwl:cwldpp:1726rr is not listed on IDEAS
    12. Annie Liang & Xiaosheng Mu & Vasilis Syrgkanis, 2022. "Dynamically Aggregating Diverse Information," Econometrica, Econometric Society, vol. 90(1), pages 47-80, January.
    13. Sims, Christopher A., 2003. "Implications of rational inattention," Journal of Monetary Economics, Elsevier, vol. 50(3), pages 665-690, April.
    14. Bruno Strulovici, 2010. "Learning While Voting: Determinants of Collective Experimentation," Econometrica, Econometric Society, vol. 78(3), pages 933-971, May.
    15. Bartosz Maćkowiak & Filip Matějka & Mirko Wiederholt, 2023. "Rational Inattention: A Review," Journal of Economic Literature, American Economic Association, vol. 61(1), pages 226-273, March.
    16. Yingni Guo, 2016. "Dynamic Delegation of Experimentation," American Economic Review, American Economic Association, vol. 106(8), pages 1969-2008, August.
    17. Janet M. Currie & W. Bentley MacLeod, 2018. "Understanding Doctor Decision Making: The Case of Depression," NBER Working Papers 24955, National Bureau of Economic Research, Inc.
    18. Yeon-Koo Che & Johannes Hörner, 2018. "Recommender Systems as Mechanisms for Social Learning," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 133(2), pages 871-925.
    19. Gilles Stoltz & Sébastien Bubeck & Rémi Munos, 2011. "Pure exploration in finitely-armed and continuous-armed bandits," Post-Print hal-00609550, HAL.
    20. Patrick Bolton & Christopher Harris, 1999. "Strategic Experimentation," Econometrica, Econometric Society, vol. 67(2), pages 349-374, March.
    21. Bergemann, Dirk & Hege, Ulrich, 1998. "Venture capital financing, moral hazard, and learning," Journal of Banking & Finance, Elsevier, vol. 22(6-8), pages 703-735, August.
    22. Annie Liang & Xiaosheng Mu, 2020. "Complementary Information and Learning Traps," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 135(1), pages 389-448.
    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. Chen, Chia-Hui & Ishida, Junichiro, 2018. "Hierarchical experimentation," Journal of Economic Theory, Elsevier, vol. 177(C), pages 365-404.
    2. Heidhues, Paul & Rady, Sven & Strack, Philipp, 2015. "Strategic experimentation with private payoffs," Journal of Economic Theory, Elsevier, vol. 159(PA), pages 531-551.
    3. Forand, Jean Guillaume, 2015. "Keeping your options open," Journal of Economic Dynamics and Control, Elsevier, vol. 53(C), pages 47-68.
    4. Mira Frick & Yuhta Ishii, 2015. "Innovation Adoption by Forward-Looking Social Learners," Cowles Foundation Discussion Papers 1877, Cowles Foundation for Research in Economics, Yale University.
    5. Jan Eeckhout & Xi Weng, 2022. "Assortative Learning," Economica, London School of Economics and Political Science, vol. 89(355), pages 647-688, July.
    6. Thomas, Caroline, 2019. "Experimentation with reputation concerns – Dynamic signalling with changing types," Journal of Economic Theory, Elsevier, vol. 179(C), pages 366-415.
    7. Yingkai Li & Jonathan Libgober, 2023. "Implementing Evidence Acquisition: Time Dependence in Contracts for Advice," Papers 2310.19147, arXiv.org, revised Sep 2024.
    8. Aubrey Clark & Giovanni Reggiani, 2021. "Contracts for acquiring information," Papers 2103.03911, arXiv.org.
    9. Thomas Greve & Hans Keiding, 2023. "A model of privately funded public research," Journal of Economics, Springer, vol. 140(1), pages 63-91, September.
    10. Weng, Xi, 2015. "Dynamic pricing in the presence of individual learning," Journal of Economic Theory, Elsevier, vol. 155(C), pages 262-299.
    11. Sorensen, Morten, 2007. "Learning by Investing: Evidence from Venture Capital," SIFR Research Report Series 53, Institute for Financial Research.
    12. Chen, Chia-Hui & Ishida, Junichiro & Mukherjee, Arijit, 2023. "Pioneer, early follower or late entrant: Entry dynamics with learning and market competition," European Economic Review, Elsevier, vol. 152(C).
    13. Johannes Hörner & Larry Samuelson, 2013. "Incentives for experimenting agents," RAND Journal of Economics, RAND Corporation, vol. 44(4), pages 632-663, December.
    14. Besanko, David & Tong, Jian & Wu, Jianjun, 2016. "Subsidizing research programs with "if" and "when" uncertainty in the face of severe informational constraints," Discussion Paper Series In Economics And Econometrics 1605, Economics Division, School of Social Sciences, University of Southampton.
    15. Khalil, Fahad & Lawarree, Jacques & Rodivilov, Alexander, 2020. "Learning from failures: Optimal contracts for experimentation and production," Journal of Economic Theory, Elsevier, vol. 190(C).
    16. Hu, Yingyao & Kayaba, Yutaka & Shum, Matthew, 2013. "Nonparametric learning rules from bandit experiments: The eyes have it!," Games and Economic Behavior, Elsevier, vol. 81(C), pages 215-231.
    17. Keller, Godfrey & Rady, Sven, 2020. "Undiscounted bandit games," Games and Economic Behavior, Elsevier, vol. 124(C), pages 43-61.
    18. Xie, Yinxi & Xie, Yang, 2017. "Machiavellian experimentation," Journal of Comparative Economics, Elsevier, vol. 45(4), pages 685-711.
    19. Caroline D. Thomas, 2021. "Strategic Experimentation with Congestion," American Economic Journal: Microeconomics, American Economic Association, vol. 13(1), pages 1-82, February.
    20. Emeric Henry & Marco Loseto & Marco Ottaviani, 2022. "Regulation with Experimentation: Ex Ante Approval, Ex Post Withdrawal, and Liability," Management Science, INFORMS, vol. 68(7), pages 5330-5347, July.

    More about this item

    JEL classification:

    • C73 - Mathematical and Quantitative Methods - - Game Theory and Bargaining Theory - - - Stochastic and Dynamic Games; Evolutionary Games
    • D81 - Microeconomics - - Information, Knowledge, and Uncertainty - - - Criteria for Decision-Making under Risk and Uncertainty
    • D83 - Microeconomics - - Information, Knowledge, and Uncertainty - - - Search; Learning; Information and Knowledge; Communication; Belief; Unawareness
    • O35 - Economic Development, Innovation, Technological Change, and Growth - - Innovation; Research and Development; Technological Change; Intellectual Property Rights - - - Social Innovation

    NEP fields

    This paper has been announced in the following NEP Reports:

    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:nbr:nberwo:32424. 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: the person in charge (email available below). General contact details of provider: https://edirc.repec.org/data/nberrus.html .

    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.