IDEAS home Printed from https://ideas.repec.org/a/eee/spapps/v200y2026ics0304414926001547.html

Risk-averse mean field games: Exploitability and non-asymptotic analysis

Author

Listed:
  • Cheng, Ziteng
  • Jaimungal, Sebastian

Abstract

In this paper, we use mean field games (MFGs) to investigate approximations of N-player games (NpGs) with uniformly symmetrically continuous heterogeneous closed-loop actions. To incorporate agents’ risk aversion (beyond the classical expected utility of total costs), we use an abstract evaluation functional for their performance criteria. Centered around the notion of exploitability, we conduct non-asymptotic analysis on the approximation capability of MFGs from the perspective of state-action distributions without requiring the uniqueness of equilibria. Under suitable assumptions, we first show that scenarios in the NpGs with large N and small average exploitabilities can be well approximated by approximate solutions of MFGs with relatively small exploitabilities. We then show that δ-mean field equilibria (MFEs) can be used to construct ε-equilibria in NpGs. Furthermore, in this general setting, we prove the existence of MFEs. This proof reveals a possible avenue for incorporating penalization for randomized action into MFGs.

Suggested Citation

  • Cheng, Ziteng & Jaimungal, Sebastian, 2026. "Risk-averse mean field games: Exploitability and non-asymptotic analysis," Stochastic Processes and their Applications, Elsevier, vol. 200(C).
  • Handle: RePEc:eee:spapps:v:200:y:2026:i:c:s0304414926001547
    DOI: 10.1016/j.spa.2026.105022
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0304414926001547
    Download Restriction: Full text may be restricted for ScienceDirect subscribers

    File URL: https://libkey.io/10.1016/j.spa.2026.105022?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

    for a different version of it.

    References listed on IDEAS

    as
    1. A. Bensoussan & K. C. J. Sung & S. C. P. Yam & S. P. Yung, 2016. "Linear-Quadratic Mean Field Games," Journal of Optimization Theory and Applications, Springer, vol. 169(2), pages 496-529, May.
    2. Erhan Bayraktar & Xin Zhang, 2019. "On non-uniqueness in mean field games," Papers 1908.06207, arXiv.org, revised Mar 2020.
    3. Acerbi, Carlo, 2002. "Spectral measures of risk: A coherent representation of subjective risk aversion," Journal of Banking & Finance, Elsevier, vol. 26(7), pages 1505-1518, July.
    4. Anthony Coache & Sebastian Jaimungal & 'Alvaro Cartea, 2022. "Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning," Papers 2206.14666, arXiv.org, revised May 2023.
    5. Jodi Dianetti & Giorgio Ferrari & Markus Fischer & Max Nendel, 2023. "A Unifying Framework for Submodular Mean Field Games," Mathematics of Operations Research, INFORMS, vol. 48(3), pages 1679-1710, August.
    6. Naci Saldi & Tamer Bas¸ ar & Maxim Raginsky, 2020. "Approximate Markov-Nash Equilibria for Discrete-Time Risk-Sensitive Mean-Field Games," Mathematics of Operations Research, INFORMS, vol. 45(4), pages 1596-1620, November.
    7. Jovanovic, Boyan & Rosenthal, Robert W., 1988. "Anonymous sequential games," Journal of Mathematical Economics, Elsevier, vol. 17(1), pages 77-87, February.
    8. Drew Fudenberg & David K. Levine, 2008. "Open-Loop and Closed-Loop Equilibria in Dynamic Games with Many Players," World Scientific Book Chapters, in: Drew Fudenberg & David K Levine (ed.), A Long-Run Collaboration On Long-Run Games, chapter 3, pages 41-58, World Scientific Publishing Co. Pte. Ltd..
    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. Jodi Dianetti & Giorgio Ferrari & Markus Fischer & Max Nendel, 2023. "A Unifying Framework for Submodular Mean Field Games," Mathematics of Operations Research, INFORMS, vol. 48(3), pages 1679-1710, August.
    2. Jian Yang, 2021. "Analysis of Markovian Competitive Situations Using Nonatomic Games," Dynamic Games and Applications, Springer, vol. 11(1), pages 184-216, March.
    3. Dianetti, Jodi & Ferrari, Giorgio & Fischer, Markus & Nendel, Max, 2022. "A Unifying Framework for Submodular Mean Field Games," Center for Mathematical Economics Working Papers 661, Center for Mathematical Economics, Bielefeld University.
    4. Dianetti, Jodi & Nendel, Max & Tangpi, Ludovic & Wang, Shichun, 2025. "Pasting of Equilibria and Donsker-type Results for Mean Field Games," Center for Mathematical Economics Working Papers 743, Center for Mathematical Economics, Bielefeld University.
    5. Haoyang Cao & Jodi Dianetti & Giorgio Ferrari, 2023. "Stationary Discounted and Ergodic Mean Field Games with Singular Controls," Mathematics of Operations Research, INFORMS, vol. 48(4), pages 1871-1898, November.
    6. Ferrari, Giorgio & Tzouanas, Ioannis, 2025. "Stationary Mean-Field Games of Singular Control under Knightian Uncertainty," Center for Mathematical Economics Working Papers 706, Center for Mathematical Economics, Bielefeld University.
    7. Naci Saldi & Tamer Başar & Maxim Raginsky, 2023. "Partially Observed Discrete-Time Risk-Sensitive Mean Field Games," Dynamic Games and Applications, Springer, vol. 13(3), pages 929-960, September.
    8. Yongxin Chen & Tryphon T. Georgiou & Michele Pavon, 2018. "Steering the Distribution of Agents in Mean-Field Games System," Journal of Optimization Theory and Applications, Springer, vol. 179(1), pages 332-357, October.
    9. Piotr Więcek, 2024. "Multiple-Population Discrete-Time Mean Field Games with Discounted and Total Payoffs: The Existence of Equilibria," Dynamic Games and Applications, Springer, vol. 14(4), pages 997-1026, September.
    10. Sina Sanjari & Naci Saldi & Serdar Yüksel, 2023. "Optimality of Independently Randomized Symmetric Policies for Exchangeable Stochastic Teams with Infinitely Many Decision Makers," Mathematics of Operations Research, INFORMS, vol. 48(3), pages 1254-1285, August.
    11. Yifan Wu & Junjie Lei & Wenjie Huang, 2026. "Adaptive Finite-Budget Training for CVaR Risk-Aware Q-Learning," Papers 2608.04305, arXiv.org.
    12. Guanxing Fu & Paulwin Graewe & Ulrich Horst & Alexandre Popier, 2021. "A Mean Field Game of Optimal Portfolio Liquidation," Mathematics of Operations Research, INFORMS, vol. 46(4), pages 1250-1281, November.
    13. Sofiane Aboura, 2014. "When the U.S. Stock Market Becomes Extreme?," Risks, MDPI, vol. 2(2), pages 1-15, May.
    14. Domagoj Demeterfi & Kathrin Glau & Linus Wunderlich, 2025. "Function approximations for counterparty credit exposure calculations," Papers 2507.09004, arXiv.org.
    15. Choo, Weihao & de Jong, Piet, 2015. "The tradeoff insurance premium as a two-sided generalisation of the distortion premium," Insurance: Mathematics and Economics, Elsevier, vol. 65(C), pages 238-246.
    16. Dimitrios G. Konstantinides & Georgios C. Zachos, 2019. "Exhibiting Abnormal Returns Under a Risk Averse Strategy," Methodology and Computing in Applied Probability, Springer, vol. 21(2), pages 551-566, June.
    17. Alois Pichler, 2013. "Premiums And Reserves, Adjusted By Distortions," Papers 1304.0490, arXiv.org.
    18. Light, Bar & Weintraub, Gabriel, 2018. "Mean Field Equilibrium: Uniqueness, Existence, and Comparative Statics," Research Papers 3731, Stanford University, Graduate School of Business.
    19. Christopher Blier-Wong & Jean-Gabriel Lauzier, 2026. "Designing entry-monotone risk-sharing pools," Papers 2606.00972, arXiv.org.
    20. Dietmar Ernst, 2023. "Risk Measures in Simulation-Based Business Valuation: Classification of Risk Measures in Risk Axiom Systems and Application in Valuation Practice," Risks, MDPI, vol. 11(1), pages 1-14, January.

    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:eee:spapps:v:200:y:2026:i:c:s0304414926001547. 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: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/505572/description#description .

    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.