IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2407.01458.html
   My bibliography  Save this paper

Contractual Reinforcement Learning: Pulling Arms with Invisible Hands

Author

Listed:
  • Jibang Wu
  • Siyu Chen
  • Mengdi Wang
  • Huazheng Wang
  • Haifeng Xu

Abstract

The agency problem emerges in today's large scale machine learning tasks, where the learners are unable to direct content creation or enforce data collection. In this work, we propose a theoretical framework for aligning economic interests of different stakeholders in the online learning problems through contract design. The problem, termed \emph{contractual reinforcement learning}, naturally arises from the classic model of Markov decision processes, where a learning principal seeks to optimally influence the agent's action policy for their common interests through a set of payment rules contingent on the realization of next state. For the planning problem, we design an efficient dynamic programming algorithm to determine the optimal contracts against the far-sighted agent. For the learning problem, we introduce a generic design of no-regret learning algorithms to untangle the challenges from robust design of contracts to the balance of exploration and exploitation, reducing the complexity analysis to the construction of efficient search algorithms. For several natural classes of problems, we design tailored search algorithms that provably achieve $\tilde{O}(\sqrt{T})$ regret. We also present an algorithm with $\tilde{O}(T^{2/3})$ for the general problem that improves the existing analysis in online contract design with mild technical assumptions.

Suggested Citation

  • Jibang Wu & Siyu Chen & Mengdi Wang & Huazheng Wang & Haifeng Xu, 2024. "Contractual Reinforcement Learning: Pulling Arms with Invisible Hands," Papers 2407.01458, arXiv.org, revised Jul 2024.
  • Handle: RePEc:arx:papers:2407.01458
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2407.01458
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Jibang Wu & Zixuan Zhang & Zhe Feng & Zhaoran Wang & Zhuoran Yang & Michael I. Jordan & Haifeng Xu, 2022. "Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learning," Papers 2202.10678, arXiv.org.
    2. Hemant K. Bhargava, 2022. "The Creator Economy: Managing Ecosystem Supply, Revenue Sharing, and Platform Design," Management Science, INFORMS, vol. 68(7), pages 5233-5251, July.
    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. Siyu Chen & Jibang Wu & Yifan Wu & Zhuoran Yang, 2023. "Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Model," Papers 2303.08613, arXiv.org, revised Aug 2023.
    2. Jin Li & Gary Pisano & Yejia Xu & Feng Zhu, 2023. "Marketplace Scalability and Strategic Use of Platform Investment," Management Science, INFORMS, vol. 69(7), pages 3958-3975, July.
    3. Chen Liang & Murat Tunc & Gordon Burtch, 2024. "Market Responses to Genuine Versus Strategic Generosity: An Empirical Examination of NFT Charity Fundraisers," Papers 2401.12064, arXiv.org.
    4. Cai, Yajun & Wu, Yibin & Xue, Weili, 2024. "Social media retailing in the creator economy," Omega, Elsevier, vol. 124(C).
    5. Foerster, Manuel & Hellmann, Tim & Vega-Redondo, Fernando, 2024. "Strategic use of social media influencer marketing," UC3M Working papers. Economics 43985, Universidad Carlos III de Madrid. Departamento de Economía.
    6. Daniel Huttenlocher & Hannah Li & Liang Lyu & Asuman Ozdaglar & James Siderius, 2023. "Matching of Users and Creators in Two-Sided Markets with Departures," Papers 2401.00313, arXiv.org, revised Jan 2024.
    7. Natalie Collina & Aaron Roth & Han Shao, 2023. "Efficient Prior-Free Mechanisms for No-Regret Agents," Papers 2311.07754, arXiv.org.
    8. Zhang, Xiaojing & Zhang, Yulin, 2024. "Content marketing in the social media platform: Examining the effect of content creation modes on the payoff of participants," Journal of Retailing and Consumer Services, Elsevier, vol. 77(C).
    9. Hemant K. Bhargava & Kitty Wang & Xingyue (Luna) Zhang, 2022. "Fending Off Critics of Platform Power with Differential Revenue Sharing: Doing Well by Doing Good?," Management Science, INFORMS, vol. 68(11), pages 8249-8260, November.
    10. Krishnamurthy Iyer & Haifeng Xu & You Zu, 2023. "Markov Persuasion Processes with Endogenous Agent Beliefs," Papers 2307.03181, arXiv.org, revised Jul 2023.

    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:2407.01458. 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.