IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2201.00345.html
   My bibliography  Save this paper

Robust Algorithmic Collusion

Author

Listed:
  • Nicolas Eschenbaum
  • Filip Mellgren
  • Philipp Zahn

Abstract

This paper develops a formal framework to assess policies of learning algorithms in economic games. We investigate whether reinforcement-learning agents with collusive pricing policies can successfully extrapolate collusive behavior from training to the market. We find that in testing environments collusion consistently breaks down. Instead, we observe static Nash play. We then show that restricting algorithms' strategy space can make algorithmic collusion robust, because it limits overfitting to rival strategies. Our findings suggest that policy-makers should focus on firm behavior aimed at coordinating algorithm design in order to make collusive policies robust.

Suggested Citation

  • Nicolas Eschenbaum & Filip Mellgren & Philipp Zahn, 2022. "Robust Algorithmic Collusion," Papers 2201.00345, arXiv.org, revised Jan 2022.
    • Handle: RePEc:arx:papers:2201.00345
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2201.00345
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Calzolari, Giacomo & Calvano, Emilio & Denicolo, Vincenzo & Pastorello, Sergio, 2021. "Algorithmic collusion with imperfect monitoring," CEPR Discussion Papers 15738, C.E.P.R. Discussion Papers.
    2. Nicolas Bondoux & Anh Quan Nguyen & Thomas Fiig & Rodrigo Acuna-Agost, 2020. "Reinforcement learning applied to airline revenue management," Journal of Revenue and Pricing Management, Palgrave Macmillan, vol. 19(5), pages 332-348, October.
    3. Rodrigo Acuna-Agost & Eoin Thomas & Alix Lhéritier, 2021. "Price elasticity estimation for deep learning-based choice models: an application to air itinerary choices," Journal of Revenue and Pricing Management, Palgrave Macmillan, vol. 20(3), pages 213-226, June.
    4. Calvano, Emilio & Calzolari, Giacomo & Denicoló, Vincenzo & Pastorello, Sergio, 2021. "Algorithmic collusion with imperfect monitoring," International Journal of Industrial Organization, Elsevier, vol. 79(C).
    5. Mailath, George J. & Samuelson, Larry, 2006. "Repeated Games and Reputations: Long-Run Relationships," OUP Catalogue, Oxford University Press, number 9780195300796.
    6. Joseph E Harrington, 2018. "Developing Competition Law For Collusion By Autonomous Artificial Agents," Journal of Competition Law and Economics, Oxford University Press, vol. 14(3), pages 331-363.
    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. Lucila Porto, 2022. "Q-Learning algorithms in a Hotelling model," Asociación Argentina de Economía Política: Working Papers 4587, Asociación Argentina de Economía Política.
    2. Martin, Simon & Rasch, Alexander, 2022. "Collusion by algorithm: The role of unobserved actions," DICE Discussion Papers 382, Heinrich Heine University Düsseldorf, Düsseldorf Institute for Competition Economics (DICE).
    3. Gonzalo Ballestero, 2021. "Collusion and Artificial Intelligence: A computational experiment with sequential pricing algorithms under stochastic costs," Young Researchers Working Papers 1, Universidad de San Andres, Departamento de Economia, revised Oct 2022.
    4. Normann, Hans-Theo & Sternberg, Martin, 2022. "Human-algorithm interaction: Algorithmic pricing in hybrid laboratory markets," DICE Discussion Papers 392, Heinrich Heine University Düsseldorf, Düsseldorf Institute for Competition Economics (DICE).
    5. Normann, Hans-Theo & Sternberg, Martin, 2023. "Human-algorithm interaction: Algorithmic pricing in hybrid laboratory markets," European Economic Review, Elsevier, vol. 152(C).
    6. Simon Martin & Alexander Rasch, 2022. "Collusion by Algorithm: The Role of Unobserved Actions," CESifo Working Paper Series 9629, CESifo.
    7. Hans-Theo Normann & Martin Sternberg, 2021. "Human-Algorithm Interaction: Algorithmic Pricing in Hybrid Laboratory Markets," Discussion Paper Series of the Max Planck Institute for Research on Collective Goods 2021_11, Max Planck Institute for Research on Collective Goods, revised 13 Apr 2022.
    8. Gonzalo Ballestero, 2022. "Collusion and Artificial Intelligence: A Computational Experiment with Sequential Pricing Algorithms under Stochastic Costs," Working Papers 118, Red Nacional de Investigadores en Economía (RedNIE).
    9. Aleksandar B. Todorov, 2022. "Algorithmic pricing and concerted behaviour – competitive challenges?," Economic Thought journal, Bulgarian Academy of Sciences - Economic Research Institute, issue 1, pages 90-107.
    10. Gonzalo Ballestero, 2021. "Collusion and Artificial Intelligence: A computational experiment with sequential pricing algorithms under stochastic costs," Asociación Argentina de Economía Política: Working Papers 4433, Asociación Argentina de Economía Política.
    11. Sinziana-Maria Rindasu & Ioan Dan Topor & Liliana Ionescu-Feleaga, 2023. "The Evolution of Management Accountants' Digital Skills in Industry 4.0: A Qualitative Approach," Oblik i finansi, Institute of Accounting and Finance, issue 1, pages 38-48, March.
    12. Martino Banchio & Giacomo Mantegazza, 2022. "Artificial Intelligence and Spontaneous Collusion," Papers 2202.05946, arXiv.org, revised Sep 2023.
    13. Pai, Mallesh & Hansen, Karsten, 2020. "Algorithmic Collusion: Supra-competitive Prices via Independent Algorithms," CEPR Discussion Papers 14372, C.E.P.R. Discussion Papers.
    14. Daehyeon Park & Doojin Ryu, 2022. "Supply chain ethics and transparency: An agent‐based model approach with Q‐learning agents," Managerial and Decision Economics, John Wiley & Sons, Ltd., vol. 43(8), pages 3331-3337, December.
    15. Zhang Xu & Wei Zhao, 2024. "On Mechanism Underlying Algorithmic Collusion," Papers 2409.01147, arXiv.org.
    16. Matthias Hettich, 2021. "Algorithmic Collusion: Insights from Deep Learning," CQE Working Papers 9421, Center for Quantitative Economics (CQE), University of Muenster.
    17. Dolgopolov, Arthur, 2024. "Reinforcement learning in a prisoner's dilemma," Games and Economic Behavior, Elsevier, vol. 144(C), pages 84-103.
    18. Sara Fish & Yannai A. Gonczarowski & Ran I. Shorrer, 2024. "Algorithmic Collusion by Large Language Models," Papers 2404.00806, arXiv.org.
    19. W. Benedikt Schmal, 2022. "From Rules to Regs: A Structural Topic Model of Collusion Research," Papers 2210.02957, arXiv.org.
    20. Juan‐Pablo Montero & Juan Ignacio Guzman, 2010. "Output‐Expanding Collusion In The Presence Of A Competitive Fringe," Journal of Industrial Economics, Wiley Blackwell, vol. 58(1), pages 106-126, March.

    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:2201.00345. 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.