IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2503.11270.html
   My bibliography  Save this paper

Exploring Competitive and Collusive Behaviors in Algorithmic Pricing with Deep Reinforcement Learning

Author

Listed:
  • Shidi Deng
  • Maximilian Schiffer
  • Martin Bichler

Abstract

Nowadays, a significant share of the business-to-consumer sector is based on online platforms like Amazon and Alibaba and uses AI for pricing strategies. This has sparked debate on whether pricing algorithms may tacitly collude to set supra-competitive prices without being explicitly designed to do so. Our study addresses these concerns by examining the risk of collusion when Reinforcement Learning (RL) algorithms are used to decide on pricing strategies in competitive markets. Prior research in this field focused on Tabular Q-learning (TQL) and led to opposing views on whether learning-based algorithms can result in supra-competitive prices. Building on this, our work contributes to this ongoing discussion by providing a more nuanced numerical study that goes beyond TQL, additionally capturing off- and on- policy Deep Reinforcement Learning (DRL) algorithms, two distinct families of DRL algorithms that recently gained attention for algorithmic pricing. We study multiple Bertrand oligopoly variants and show that algorithmic collusion depends on the algorithm used. In our experiments, we observed that TQL tends to exhibit higher collusion and price dispersion. Moreover, it suffers from instability and disparity, as agents with higher learning rates consistently achieve higher profits, and it lacks robustness in state representation, with pricing dynamics varying significantly based on information access. In contrast, DRL algorithms, such as PPO and DQN, generally converge to lower prices closer to the Nash equilibrium. Additionally, we show that when pre-trained TQL agents interact with DRL agents, the latter quickly outperforms the former, highlighting the advantages of DRL in pricing competition. Lastly, we find that competition between heterogeneous DRL algorithms, such as PPO and DQN, tends to reduce the likelihood of supra-competitive pricing.

Suggested Citation

  • Shidi Deng & Maximilian Schiffer & Martin Bichler, 2025. "Exploring Competitive and Collusive Behaviors in Algorithmic Pricing with Deep Reinforcement Learning," Papers 2503.11270, arXiv.org.
  • Handle: RePEc:arx:papers:2503.11270
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2503.11270
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Abada, Ibrahim & Lambin, Xavier & Tchakarov, Nikolay, 2024. "Collusion by mistake: Does algorithmic sophistication drive supra-competitive profits?," European Journal of Operational Research, Elsevier, vol. 318(3), pages 927-953.
    2. Kutschinski, Erich & Uthmann, Thomas & Polani, Daniel, 2003. "Learning competitive pricing strategies by multi-agent reinforcement learning," Journal of Economic Dynamics and Control, Elsevier, vol. 27(11-12), pages 2207-2218, September.
    3. Zach Y. Brown & Alexander MacKay, 2023. "Competition in Pricing Algorithms," American Economic Journal: Microeconomics, American Economic Association, vol. 15(2), pages 109-156, May.
    4. Ajay Agrawal & Joshua Gans & Avi Goldfarb, 2019. "The Economics of Artificial Intelligence: An Agenda," NBER Books, National Bureau of Economic Research, Inc, number agra-1, October.
    5. Alexander Kastius & Rainer Schlosser, 2022. "Dynamic pricing under competition using reinforcement learning," Journal of Revenue and Pricing Management, Palgrave Macmillan, vol. 21(1), pages 50-63, February.
    6. Rana, Rupal & Oliveira, Fernando S., 2014. "Real-time dynamic pricing in a non-stationary environment using model-free reinforcement learning," Omega, Elsevier, vol. 47(C), pages 116-126.
    7. Ibrahim Abada & Xavier Lambin, 2023. "Artificial Intelligence: Can Seemingly Collusive Outcomes Be Avoided?," Management Science, INFORMS, vol. 69(9), pages 5042-5065, September.
    8. Werner, Tobias, 2023. "Algorithmic and Human Collusion," VfS Annual Conference 2023 (Regensburg): Growth and the "sociale Frage" 277573, Verein für Socialpolitik / German Economic Association.
    9. Kutschinski, Erich & Uthmann, Thomas & Polani, Daniel, 2003. "Learning competitive pricing strategies by multi-agent reinforcement learning," Journal of Economic Dynamics and Control, Elsevier, vol. 27(11), pages 2207-2218.
    10. Levitan, Richard & Shubik, Martin, 1972. "Price Duopoly and Capacity Constraints," International Economic Review, Department of Economics, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association, vol. 13(1), pages 111-122, February.
    11. Marcus Buckmann & Andy Haldane & Anne-Caroline Hüser, 2021. "Comparing minds and machines: implications for financial stability," Oxford Review of Economic Policy, Oxford University Press and Oxford Review of Economic Policy Limited, vol. 37(3), pages 479-508.
    12. Timo Klein, 2021. "Autonomous algorithmic collusion: Q‐learning under sequential pricing," RAND Journal of Economics, RAND Corporation, vol. 52(3), pages 538-558, September.
    13. Emilio Calvano & Giacomo Calzolari & Vincenzo Denicolò & Sergio Pastorello, 2020. "Artificial Intelligence, Algorithmic Pricing, and Collusion," American Economic Review, American Economic Association, vol. 110(10), pages 3267-3297, October.
    14. Stephanie Assad & Robert Clark & Daniel Ershov & Lei Xu, 2020. "Algorithmic Pricing and Competition: Empirical Evidence from the German Retail Gasoline Market," Working Paper 1438, Economics Department, Queen's University.
    15. 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.
    16. Janusz M. Meylahn & Arnoud V. den Boer, 2022. "Learning to Collude in a Pricing Duopoly," Manufacturing & Service Operations Management, INFORMS, vol. 24(5), pages 2577-2594, September.
    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. Shidi Deng & Maximilian Schiffer & Martin Bichler, 2024. "Algorithmic Collusion in Dynamic Pricing with Deep Reinforcement Learning," Papers 2406.02437, arXiv.org.
    2. 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.
    3. Justin P. Johnson & Andrew Rhodes & Matthijs Wildenbeest, 2023. "Platform Design When Sellers Use Pricing Algorithms," Econometrica, Econometric Society, vol. 91(5), pages 1841-1879, September.
    4. Epivent, Andréa & Lambin, Xavier, 2024. "On algorithmic collusion and reward–punishment schemes," Economics Letters, Elsevier, vol. 237(C).
    5. John Asker & Chaim Fershtman & Ariel Pakes, 2024. "The impact of artificial intelligence design on pricing," Journal of Economics & Management Strategy, Wiley Blackwell, vol. 33(2), pages 276-304, March.
    6. Fourberg, Niklas & Marques-Magalhaes, Katrin & Wiewiorra, Lukas, 2022. "They are among us: Pricing behavior of algorithms in the field," WIK Working Papers 6, WIK Wissenschaftliches Institut für Infrastruktur und Kommunikationsdienste GmbH, Bad Honnef.
    7. Fourberg, Niklas & Marques Magalhaes, Katrin & Wiewiorra, Lukas, 2023. "They Are Among Us: Pricing Behavior of Algorithms in the Field," 32nd European Regional ITS Conference, Madrid 2023: Realising the digital decade in the European Union – Easier said than done? 277958, International Telecommunications Society (ITS).
    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. Werner, Tobias, 2021. "Algorithmic and human collusion," DICE Discussion Papers 372, Heinrich Heine University Düsseldorf, Düsseldorf Institute for Competition Economics (DICE).
    10. Hanspach, Philip & Sapi, Geza & Wieting, Marcel, 2024. "Algorithms in the marketplace: An empirical analysis of automated pricing in e-commerce," Information Economics and Policy, Elsevier, vol. 69(C).
    11. Eshwar Ram Arunachaleswaran & Natalie Collina & Sampath Kannan & Aaron Roth & Juba Ziani, 2024. "Algorithmic Collusion Without Threats," Papers 2409.03956, arXiv.org, revised Dec 2024.
    12. Jason D. Hartline & Sheng Long & Chenhao Zhang, 2024. "Regulation of Algorithmic Collusion," Papers 2401.15794, arXiv.org, revised Sep 2024.
    13. Normann, Hans-Theo & Sternberg, Martin, 2023. "Human-algorithm interaction: Algorithmic pricing in hybrid laboratory markets," European Economic Review, Elsevier, vol. 152(C).
    14. Leonardo Madio & Aldo Pignataro, 2022. "Collusion sustainability with a capacity constrained firm," "Marco Fanno" Working Papers 0295, Dipartimento di Scienze Economiche "Marco Fanno".
    15. Simon Martin & Alexander Rasch, 2022. "Collusion by Algorithm: The Role of Unobserved Actions," CESifo Working Paper Series 9629, CESifo.
    16. Zexin Ye, 2025. "Algorithmic Collusion under Observed Demand Shocks," Papers 2502.15084, arXiv.org.
    17. Leonardo Madio & Aldo Pignataro, 2022. "Collusion Sustainability with a Capacity Constrained Firm," CESifo Working Paper Series 10170, CESifo.
    18. Torsten J. Gerpott & Jan Berends, 2022. "Competitive pricing on online markets: a literature review," Journal of Revenue and Pricing Management, Palgrave Macmillan, vol. 21(6), pages 596-622, December.
    19. Marcel Wieting & Geza Sapi, 2021. "Algorithms in the Marketplace: An Empirical Analysis of Automated Pricing in E-Commerce," Working Papers 21-06, NET Institute.
    20. Yiquan Gu & Leonardo Madio & Carlo Reggiani, 2019. "Exclusive Data, Price Manipulation and Market Leadership," CESifo Working Paper Series 7853, CESifo.

    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:arx:papers:2503.11270. 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.