IDEAS home Printed from https://ideas.repec.org/a/eee/chsofr/v174y2023ics0960077923007038.html
   My bibliography  Save this article

Deep learning for Mean Field Games with non-separable Hamiltonians

Author

Listed:
  • Assouli, Mouhcine
  • Missaoui, Badr

Abstract

This paper introduces a new method based on Deep Galerkin Methods (DGMs) for solving high-dimensional stochastic Mean Field Games (MFGs). We achieve this by using two neural networks to approximate the unknown solutions of the MFG system and forward–backward conditions. Our method is efficient, even with a small number of iterations, and is capable of handling up to 300 dimensions with a single layer, which makes it faster than other approaches. In contrast, methods based on Generative Adversarial Networks (GANs) cannot solve MFGs with non-separable Hamiltonians. We demonstrate the effectiveness of our approach by applying it to a traffic flow problem, which was previously solved using the Newton iteration method only in the deterministic case. We compare the results of our method to analytical solutions and previous approaches, showing its efficiency. We also prove the convergence of our neural network approximation with a single hidden layer using the universal approximation theorem.

Suggested Citation

  • Assouli, Mouhcine & Missaoui, Badr, 2023. "Deep learning for Mean Field Games with non-separable Hamiltonians," Chaos, Solitons & Fractals, Elsevier, vol. 174(C).
    • Handle: RePEc:eee:chsofr:v:174:y:2023:i:c:s0960077923007038
    DOI: 10.1016/j.chaos.2023.113802
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0960077923007038
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.chaos.2023.113802?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 search for a different version of it.

    References listed on IDEAS

    as
    1. Yves Achdou & Jiequn Han & Jean-Michel Lasry & Pierre-Louis Lions & Benjamin Moll, 2017. "Income and Wealth Distribution in Macroeconomics: A Continuous-Time Approach," NBER Working Papers 23732, National Bureau of Economic Research, Inc.
    2. Magnus Wiese & Lianjun Bai & Ben Wood & Hans Buehler, 2019. "Deep Hedging: Learning to Simulate Equity Option Markets," Papers 1911.01700, arXiv.org.
    3. Geroliminis, Nikolas & Daganzo, Carlos F., 2008. "Existence of urban-scale macroscopic fundamental diagrams: Some experimental findings," Transportation Research Part B: Methodological, Elsevier, vol. 42(9), pages 759-770, November.
    4. Justin Sirignano & Konstantinos Spiliopoulos, 2017. "DGM: A deep learning algorithm for solving partial differential equations," Papers 1708.07469, arXiv.org, revised Sep 2018.
    5. Keyvan-Ekbatani, Mehdi & Kouvelas, Anastasios & Papamichail, Ioannis & Papageorgiou, Markos, 2012. "Exploiting the fundamental diagram of urban networks for feedback-based gating," Transportation Research Part B: Methodological, Elsevier, vol. 46(10), pages 1393-1403.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Assouli, Mouhcine & Missaoui, Badr, 2024. "Deep Policy Iteration for high-dimensional mean field games," Applied Mathematics and Computation, Elsevier, vol. 481(C).

    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. Su, Z.C. & Chow, Andy H.F. & Fang, C.L. & Liang, E.M. & Zhong, R.X., 2023. "Hierarchical control for stochastic network traffic with reinforcement learning," Transportation Research Part B: Methodological, Elsevier, vol. 167(C), pages 196-216.
    2. Kouvelas, Anastasios & Saeedmanesh, Mohammadreza & Geroliminis, Nikolas, 2017. "Enhancing model-based feedback perimeter control with data-driven online adaptive optimization," Transportation Research Part B: Methodological, Elsevier, vol. 96(C), pages 26-45.
    3. Wada, Kentaro & Satsukawa, Koki & Smith, Mike & Akamatsu, Takashi, 2019. "Network throughput under dynamic user equilibrium: Queue spillback, paradox and traffic control," Transportation Research Part B: Methodological, Elsevier, vol. 126(C), pages 391-413.
    4. Ampountolas, Konstantinos & Zheng, Nan & Geroliminis, Nikolas, 2017. "Macroscopic modelling and robust control of bi-modal multi-region urban road networks," Transportation Research Part B: Methodological, Elsevier, vol. 104(C), pages 616-637.
    5. Haddad, Jack & Ramezani, Mohsen & Geroliminis, Nikolas, 2013. "Cooperative traffic control of a mixed network with two urban regions and a freeway," Transportation Research Part B: Methodological, Elsevier, vol. 54(C), pages 17-36.
    6. Yildirimoglu, Mehmet & Sirmatel, Isik Ilber & Geroliminis, Nikolas, 2018. "Hierarchical control of heterogeneous large-scale urban road networks via path assignment and regional route guidance," Transportation Research Part B: Methodological, Elsevier, vol. 118(C), pages 106-123.
    7. Mohajerpoor, Reza & Saberi, Meead & Vu, Hai L. & Garoni, Timothy M. & Ramezani, Mohsen, 2020. "H∞ robust perimeter flow control in urban networks with partial information feedback," Transportation Research Part B: Methodological, Elsevier, vol. 137(C), pages 47-73.
    8. Niu, Xiao-Jing & Zhao, Xiao-Mei & Xie, Dong-Fan & Liu, Feng & Bi, Jun & Lu, Chaoru, 2022. "Impact of large-scale activities on macroscopic fundamental diagram: Field data analysis and modeling," Transportation Research Part A: Policy and Practice, Elsevier, vol. 161(C), pages 241-268.
    9. Guo, Qiangqiang & Ban, Xuegang (Jeff), 2020. "Macroscopic fundamental diagram based perimeter control considering dynamic user equilibrium," Transportation Research Part B: Methodological, Elsevier, vol. 136(C), pages 87-109.
    10. Alonso, Borja & Ibeas, Ángel & Musolino, Giuseppe & Rindone, Corrado & Vitetta, Antonino, 2019. "Effects of traffic control regulation on Network Macroscopic Fundamental Diagram: A statistical analysis of real data," Transportation Research Part A: Policy and Practice, Elsevier, vol. 126(C), pages 136-151.
    11. Gao, Shengling & Li, Daqing & Zheng, Nan & Hu, Ruiqi & She, Zhikun, 2022. "Resilient perimeter control for hyper-congested two-region networks with MFD dynamics," Transportation Research Part B: Methodological, Elsevier, vol. 156(C), pages 50-75.
    12. Amirgholy, Mahyar & Shahabi, Mehrdad & Gao, H. Oliver, 2017. "Optimal design of sustainable transit systems in congested urban networks: A macroscopic approach," Transportation Research Part E: Logistics and Transportation Review, Elsevier, vol. 103(C), pages 261-285.
    13. Li, Xinghua & Zhang, Xinyuan & Qian, Xinwu & Zhao, Cong & Guo, Yuntao & Peeta, Srinivas, 2024. "Beyond centralization: Non-cooperative perimeter control with extended mean-field reinforcement learning in urban road networks," Transportation Research Part B: Methodological, Elsevier, vol. 186(C).
    14. Haddad, Jack & Shraiber, Arie, 2014. "Robust perimeter control design for an urban region," Transportation Research Part B: Methodological, Elsevier, vol. 68(C), pages 315-332.
    15. Ramezani, Mohsen & Haddad, Jack & Geroliminis, Nikolas, 2015. "Dynamics of heterogeneity in urban networks: aggregated traffic modeling and hierarchical control," Transportation Research Part B: Methodological, Elsevier, vol. 74(C), pages 1-19.
    16. Ji, Yuxuan & Geroliminis, Nikolas, 2012. "On the spatial partitioning of urban transportation networks," Transportation Research Part B: Methodological, Elsevier, vol. 46(10), pages 1639-1656.
    17. Wu, Chao-Yun & Li, Ming & Jiang, Rui & Hao, Qing-Yi & Hu, Mao-Bin, 2018. "Perimeter control for urban traffic system based on macroscopic fundamental diagram," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 503(C), pages 231-242.
    18. Knoop, Victor L. & van Lint, Hans & Hoogendoorn, Serge P., 2015. "Traffic dynamics: Its impact on the Macroscopic Fundamental Diagram," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 438(C), pages 236-250.
    19. Xu, Guanhao & Gayah, Vikash V., 2023. "Non-unimodal and non-concave relationships in the network Macroscopic Fundamental Diagram caused by hierarchical streets," Transportation Research Part B: Methodological, Elsevier, vol. 173(C), pages 203-227.
    20. Haddad, Jack & Zheng, Zhengfei, 2020. "Adaptive perimeter control for multi-region accumulation-based models with state delays," Transportation Research Part B: Methodological, Elsevier, vol. 137(C), pages 133-153.

    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:chsofr:v:174:y:2023:i:c:s0960077923007038. 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: Thayer, Thomas R. (email available below). General contact details of provider: https://www.journals.elsevier.com/chaos-solitons-and-fractals .

    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.