IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2410.17086.html
   My bibliography  Save this paper

Exploration and Persuasion

Author

Listed:
  • Aleksandrs Slivkins

Abstract

How to incentivize self-interested agents to explore when they prefer to exploit? Consider a population of self-interested agents that make decisions under uncertainty. They "explore" to acquire new information and "exploit" this information to make good decisions. Collectively they need to balance these two objectives, but their incentives are skewed toward exploitation. This is because exploration is costly, but its benefits are spread over many agents in the future. "Incentivized Exploration" addresses this issue via strategic communication. Consider a benign ``principal" which can communicate with the agents and make recommendations, but cannot force the agents to comply. Moreover, suppose the principal can observe the agents' decisions and the outcomes of these decisions. The goal is to design a communication and recommendation policy which (i) achieves a desirable balance between exploration and exploitation, and (ii) incentivizes the agents to follow recommendations. What makes it feasible is "information asymmetry": the principal knows more than any one agent, as it collects information from many. It is essential that the principal does not fully reveal all its knowledge to the agents. Incentivized exploration combines two important problems in, resp., machine learning and theoretical economics. First, if agents always follow recommendations, the principal faces a multi-armed bandit problem: essentially, design an algorithm that balances exploration and exploitation. Second, interaction with a single agent corresponds to "Bayesian persuasion", where a principal leverages information asymmetry to convince an agent to take a particular action. We provide a brief but self-contained introduction to each problem through the lens of incentivized exploration, solving a key special case of the former as a sub-problem of the latter.

Suggested Citation

  • Aleksandrs Slivkins, 2024. "Exploration and Persuasion," Papers 2410.17086, arXiv.org.
  • Handle: RePEc:arx:papers:2410.17086
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2410.17086
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Dirk Bergemann & Stephen Morris, 2019. "Information Design: A Unified Perspective," Journal of Economic Literature, American Economic Association, vol. 57(1), pages 44-95, March.
    2. Emir Kamenica, 2019. "Bayesian Persuasion and Information Design," Annual Review of Economics, Annual Reviews, vol. 11(1), pages 249-272, August.
    3. 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.
    4. Yiangos Papanastasiou & Kostas Bimpikis & Nicos Savva, 2018. "Crowdsourcing Exploration," Management Science, INFORMS, vol. 64(4), pages 1727-1746, April.
    5. Hamsa Bastani & Mohsen Bayati & Khashayar Khosravi, 2021. "Mostly Exploration-Free Algorithms for Contextual Bandits," Management Science, INFORMS, vol. 67(3), pages 1329-1349, March.
    6. Daron Acemoglu & Ali Makhdoumi & Azarakhsh Malekian & Asuman Ozdaglar, 2022. "Learning From Reviews: The Selection Effect and the Speed of Learning," Econometrica, Econometric Society, vol. 90(6), pages 2857-2899, November.
    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. Anand Kalvit & Aleksandrs Slivkins & Yonatan Gur, 2024. "Incentivized Exploration via Filtered Posterior Sampling," Papers 2402.13338, arXiv.org.
    2. Yingkai Li & Aleksandrs Slivkins, 2022. "Exploration and Incentivizing Participation in Clinical Trials," Papers 2202.06191, arXiv.org, revised Aug 2024.
    3. Jerry Anunrojwong & Krishnamurthy Iyer & David Lingenbrink, 2024. "Persuading Risk-Conscious Agents: A Geometric Approach," Operations Research, INFORMS, vol. 72(1), pages 151-166, January.
    4. Zheng, Shiyuan & Jia, Rongwen & Shang, Wen-Long & Fu, Xiaowen & Wang, Kun, 2023. "Promote transport facility Resilience: Persuasion or Subsidy?," Transportation Research Part A: Policy and Practice, Elsevier, vol. 176(C).
    5. Roesler, Anne-Katrin & Deb, Rahul, 2021. "Multi-Dimensional Screening: Buyer-Optimal Learning and Informational Robustness," CEPR Discussion Papers 16206, C.E.P.R. Discussion Papers.
    6. Eduardo Perez‐Richet & Vasiliki Skreta, 2022. "Test Design Under Falsification," Econometrica, Econometric Society, vol. 90(3), pages 1109-1142, May.
    7. Victor F. Araman & René A. Caldentey, 2022. "Diffusion Approximations for a Class of Sequential Experimentation Problems," Management Science, INFORMS, vol. 68(8), pages 5958-5979, August.
    8. Shih-Tang Su & Vijay G. Subramanian & Grant Schoenebeck, 2021. "Bayesian Persuasion in Sequential Trials," Papers 2110.09594, arXiv.org, revised Nov 2021.
    9. Heski Bar‐Isaac & Clare Leaver, 2022. "Training, Recruitment, and Outplacement as Endogenous Adverse Selection," Economica, London School of Economics and Political Science, vol. 89(356), pages 849-861, October.
    10. Bonatti, Alessandro & Dahleh, Munther & Horel, Thibaut & Nouripour, Amir, 2024. "Selling information in competitive environments," Journal of Economic Theory, Elsevier, vol. 216(C).
    11. Li Chen & Yiangos Papanastasiou, 2021. "Seeding the Herd: Pricing and Welfare Effects of Social Learning Manipulation," Management Science, INFORMS, vol. 67(11), pages 6734-6750, November.
    12. Raphaela Hennigs, 2021. "Conflict prevention by Bayesian persuasion," Journal of Public Economic Theory, Association for Public Economic Theory, vol. 23(4), pages 710-731, August.
    13. Guillaume R. Fréchette & Alessandro Lizzeri & Jacopo Perego, 2022. "Rules and Commitment in Communication: An Experimental Analysis," Econometrica, Econometric Society, vol. 90(5), pages 2283-2318, September.
    14. Little, Andrew T., 2022. "Bayesian Explanations for Persuasion," OSF Preprints ygw8e, Center for Open Science.
    15. Hiroto Sato, 2023. "Robust implementation in sequential information design under supermodular payoffs and objective," Review of Economic Design, Springer;Society for Economic Design, vol. 27(2), pages 269-285, June.
    16. Mark Armstrong & Jidong Zhou, 2022. "Consumer Information and the Limits to Competition," American Economic Review, American Economic Association, vol. 112(2), pages 534-577, February.
    17. Kimon Drakopoulos & Shobhit Jain & Ramandeep Randhawa, 2021. "Persuading Customers to Buy Early: The Value of Personalized Information Provisioning," Management Science, INFORMS, vol. 67(2), pages 828-853, February.
    18. Wu, Haoyang, 2022. "A type-adjustable mechanism where the designer may obtain more payoffs by optimally controlling distributions of agents' types," MPRA Paper 113150, University Library of Munich, Germany.
    19. Whitmeyer, Joseph & Whitmeyer, Mark, 2021. "Mixtures of mean-preserving contractions," Journal of Mathematical Economics, Elsevier, vol. 94(C).
    20. Monte, Daniel & Linhares, Luis Henrique, 2023. "Stealth Startups, Clauses, and Add-ons: A Model of Strategic Obfuscation," MPRA Paper 115926, University Library of Munich, Germany.

    More about this item

    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:arx:papers:2410.17086. 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: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    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.