A Machine Learning Method for Stackelberg Mean Field Games

References

• [1] Achdou Y, Capuzzo-Dolcetta I (2010) Mean field games: Numerical methods. SIAM J. Numer. Anal. 48(3):1136–1162.Crossref, Google Scholar
• [2] Achdou Y, Laurière M (2020) Mean field games and applications: Numerical aspects. Cardaliaguet P, Porretta A, eds. Mean Field Games, Lecture Notes in Mathematics, vol. 2281 (Springer, Cham, Switzerland), 249–307.Crossref, Google Scholar
• [3] Achdou Y, Camilli F, Capuzzo-Dolcetta I (2012) Mean field games: Numerical methods for the planning problem. SIAM J. Control Optim. 50(1):77–109.Crossref, Google Scholar
• [4] Alvarez GA, Nadtochiy S (2023) Optimal contract design via relaxation: Application to the problem of brokerage fee for a client with private signal. Preprint, submitted July 13, https://arxiv.org/abs/2307.07010.Google Scholar
• [5] Angiuli A, Graves CV, Li H, Chassagneux JF, Delarue F, Carmona R (2019) Cemracs 2017: Numerical probabilistic approach to MFG. ESAIM Proc. Surveys 65:84–113.Crossref, Google Scholar
• [6] Aurell A, Carmona R, Dayanıklı G, Laurière M (2022) Optimal incentives to mitigate epidemics: A Stackelberg mean field game approach. SIAM J. Control Optim. 60(2):S294–S322.Crossref, Google Scholar
• [7] Bensoussan A, Chau MHM, Yam SCP (2015) Mean field Stackelberg games: Aggregation of delayed instructions. SIAM J. Control Optim. 53(4):2237–2266.Crossref, Google Scholar
• [8] Bensoussan A, Chau MHM, Yam SCP (2016) Mean field games with a dominating player. Appl. Math. Optim. 74(1):91–128.Crossref, Google Scholar
• [9] Bensoussan A, Chen S, Sethi SP (2015) The maximum principle for global solutions of stochastic Stackelberg differential games. SIAM J. Control Optim. 53(4):1956–1981.Crossref, Google Scholar
• [10] Bensoussan A, Frehse J, Yam P (2013) Mean Field Games and Mean Field Type Control Theory, SpringerBriefs in Mathematics, vol. 101 (Springer, New York).Crossref, Google Scholar
• [11] Bensoussan A, Chau M, Lai Y, Yam SCP (2017) Linear-quadratic mean field Stackelberg games with state and control delays. SIAM J. Control Optim. 55(4):2748–2781.Crossref, Google Scholar
• [12] Bergault P, Cardaliaguet P, Rainer C (2024) Mean field games in a Stackelberg problem with an informed major player. SIAM J. Control Optim. 62(3):1737–1765.Crossref, Google Scholar
• [13] Briceno-Arias LM, Kalise D, Silva FJ (2018) Proximal methods for stationary mean field games with local couplings. SIAM J. Control Optim. 56(2):801–836.Crossref, Google Scholar
• [14] Campbell S, Chen Y, Shrivats A, Jaimungal S (2021) Deep learning for principal-agent mean field games. Preprint, submitted October 3, https://arxiv.org/abs/2110.01127.Google Scholar
• [15] Cardaliaguet P, Cirant M, Porretta A (2020) Remarks on Nash equilibria in mean field game models with a major player. Proc. Amer. Math. Soc. 148(10):4241–4255.Crossref, Google Scholar
• [16] Carlini E, Silva FJ (2014) A fully discrete semi-Lagrangian scheme for a first order mean field game problem. SIAM J. Numer. Anal. 52(1):45–67.Crossref, Google Scholar
• [17] Carmona R, Dayanıklı G (2021) Mean field game model for an advertising competition in a duopoly. Internat. Game Theory Rev. 23(04):2150024.Crossref, Google Scholar
• [18] Carmona R, Delarue F (2018) Probabilistic Theory of Mean Field Games with Applications I: Mean Field FBSDEs, Control, and Games, Probability Theory and Stochastic Modelling, vol. 83 (Springer International Publishing, Cham, Switzerland).Google Scholar
• [19] Carmona R, Delarue F (2018) Probabilistic Theory of Mean Field Games with Applications II: Mean Field Games with Common Noise and Master Equations, Probability Theory and Stochastic Modelling, vol. 84 (Springer International Publishing, Cham, Switzerland).Crossref, Google Scholar
• [20] Carmona R, Laurière M (2022) Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games: II—The finite horizon case. Ann. Appl. Probab. 32(6):4065–4105.Crossref, Google Scholar
• [21] Carmona R, Wang P (2016) An alternative approach to mean field game with major and minor players, and applications to herders impacts. Appl. Math. Optim. 76:5–27.Crossref, Google Scholar
• [22] Carmona R, Wang P (2021) Finite-state contract theory with a principal and a field of agents. Management Sci. 67(8):4725–4741.Link, Google Scholar
• [23] Carmona RA, Zhu X (2016) A probabilistic approach to mean field games with major and minor players. Ann. Appl. Probab. 26(3):1535–1580.Crossref, Google Scholar
• [24] Carmona R, Dayanıklı G, Laurière M (2022) Mean field models to regulate carbon emissions in electricity production. Dynam. Games Appl. 12(3):897–928.Crossref, Google Scholar
• [25] Chassagneux JF, Crisan D, Delarue F (2019) Numerical method for FBSDEs of McKean–Vlasov type. Ann. Appl. Probab. 29(3):1640–1684.Crossref, Google Scholar
• [26] Cui K, Dayanıklı G, Laurière M, Geist M, Pietquin O, Koeppl H (2024) Learning discrete-time major-minor mean field games. Proc. AAAI Conf. Artificial Intelligence 38(9):9616–9625.Google Scholar
• [27] Cvitanić J, Possamaï D, Touzi N (2018) Dynamic programming approach to principal–agent problems. Finance Stochastics 22(1):1–37.Crossref, Google Scholar
• [28] Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math. Control Signals Systems 2(4):303–314.Crossref, Google Scholar
• [29] Dayanikli G, Laurière M, Zhang J (2024) Deep learning for population-dependent controls in mean field control problems with common noise. Proc. 23rd Internat. Conf. Autonomous Agents Multiagent Systems (International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC), 2231–2233.Google Scholar
• [30] Djehiche B, Helgesson P (2014) The principal-agent problem; a stochastic maximum principle approach. Preprint, submitted October 23, https://arxiv.org/abs/1410.6392.Google Scholar
• [31] Djete MF (2023) Stackelberg mean field games: Convergence and existence results to the problem of principal with multiple agents in competition. Preprint, submitted August 23, https://arxiv.org/abs/2309.00640.Google Scholar
• [32] Elie R, Mastrolia T, Possamaï D (2019) A tale of a principal and many, many agents. Math. Oper. Res. 44(2):440–467.Link, Google Scholar
• [33] Elie R, Hubert E, Mastrolia T, Possamaï D (2021) Mean-field moral hazard for optimal energy demand response management. Math. Finance 31(1):399–473.Crossref, Google Scholar
• [34] Fouque JP, Zhang Z (2020) Deep learning methods for mean field control problems with delay. Frontiers Appl. Math. Statist. 6(11):1–17.Crossref, Google Scholar
• [35] Fu G, Horst U (2020) Mean-field leader-follower games with terminal state constraint. SIAM J. Control Optim. 58(4):2078–2113.Crossref, Google Scholar
• [36] Germain M, Laurière M, Pham H, Warin X (2022) DeepSets and their derivative networks for solving symmetric PDEs. J. Sci. Comput. 91(2):63.Crossref, Google Scholar
• [37] Gomes D, Gutierrez J, Laurière M (2023) Machine learning architectures for price formation models. Appl. Math. Optim. 88(1):23.Crossref, Google Scholar
• [38] Guo X, Hu A, Zhang J (2022) Optimization frameworks and sensitivity analysis of Stackelberg mean-field games. Preprint, submitted October 8, https://arxiv.org/abs/2210.04110.Google Scholar
• [39] Han J, Hu R (2021) Recurrent neural networks for stochastic control problems with delay. Math. Control Signals Systems 33(4):775–795.Crossref, Google Scholar
• [40] Holmstrom B, Milgrom P (1987) Aggregation and linearity in the provision of intertemporal incentives. Econometrica 55(2):303–328.Crossref, Google Scholar
• [41] Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Networks 4(2):251–257.Crossref, Google Scholar
• [42] Hornik K, Stinchcombe M, White H (1990) Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Networks 3(5):551–560.Crossref, Google Scholar
• [43] Hu K, Ren Z, Yang J (2022) Principal-agent problem with multiple principals. Stochastics 95(5):878–905.Crossref, Google Scholar
• [44] Huang M (2010) Large-population LQG games involving a major player: The Nash certainty equivalence principle. SIAM J. Control Optim. 48(5):3318–3353.Crossref, Google Scholar
• [45] Huang M, Caines PE, Malhamé RP (2007) Large-population cost-coupled LQG problems with nonuniform agents: Individual-mass behavior and decentralized ϵ-Nash equilibria. IEEE Trans. Automatic Control 52(9):1560–1571.Crossref, Google Scholar
• [46] Huang M, Malhamé RP, Caines PE (2006) Large population stochastic dynamic games: Closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle. Comm. Inform. Systems 6(3):221–252.Crossref, Google Scholar
• [47] Hubert E, Mastrolia T, Possamaï D, Warin X (2022) Incentives, lockdown, and testing: From Thucydides’ analysis to the COVID-19 pandemic. J. Math. Biol. 84(5):37.Crossref, Google Scholar
• [48] Kršek D, Possamaï D (2023) Randomisation with moral hazard: A path to existence of optimal contracts. Preprint, submitted November 22, https://arxiv.org/abs/2311.13278.Google Scholar
• [49] Lasry JM, Lions PL (2006) Jeux à champ moyen. I–le cas stationnaire. Comptes Rendus Math. 343(9):619–625.Crossref, Google Scholar
• [50] Lasry JM, Lions PL (2006) Jeux à champ moyen. II–horizon fini et contrôle optimal. Comptes Rendus Math. 343(10):679–684.Crossref, Google Scholar
• [51] Lasry JM, Lions PL (2018) Mean-field games with a major player. Comptes Rendus Math. 356(8):886–890.Crossref, Google Scholar
• [52] Lin Y, Jiang X, Zhang W (2018) An open-loop Stackelberg strategy for the linear quadratic mean-field stochastic differential game. IEEE Trans. Automatic Control 64(1):97–110.Crossref, Google Scholar
• [53] Mastrolia T, Zhang J (2022) Agency problem and mean field system of agents with moral hazard, synergistic effects and accidents. Preprint, submitted July 22, https://arxiv.org/abs/2207.11087.Google Scholar
• [54] Mhaskar HN, Micchelli CA (1995) Degree of approximation by neural and translation networks with a single hidden layer. Adv. Appl. Math. 16(2):151–183.Crossref, Google Scholar
• [55] Min M, Hu R (2021) Signatured deep fictitious play for mean field games with common noise. Meila M, Zhang T, eds. Proc. 38th Internat. Conf. Machine Learn., vol. 139 (PMLR, New York), 7736–7747.Google Scholar
• [56] Moon J, Başar T (2018) Linear quadratic mean field Stackelberg differential games. Automatica 97:200–213.Crossref, Google Scholar
• [57] Nguyen SL, Huang M (2012) Linear-quadratic-Gaussian mixed games with continuum-parametrized minor players. SIAM J. Control Optim. 50(5):2907–2937.Crossref, Google Scholar
• [58] Nourian M, Caines PE (2013) ϵ-Nash mean field game theory for nonlinear stochastic dynamical systems with major and minor agents. SIAM J. Control Optim. 51(4):3302–3331.Crossref, Google Scholar
• [59] Nourian M, Caines PE, Malhamé RP, Huang M (2012) Mean field LQG control in leader-follower stochastic multi-agent systems: Likelihood ratio based adaptation. IEEE Trans. Automatic Control 57(11):2801–2816.Crossref, Google Scholar
• [60] Oner A, Gunel GO, Saldı N (2018) Mean field multilayer Stackelberg differential games in multi-agent systems. Appl. Comput. Math. 17(1):72–95.Google Scholar
• [61] Perrin S, Laurière M, Pérolat J, Élie R, Geist M, Pietquin O (2022) Generalization in mean field games by learning master policies. Proc. AAAI Conf. Artificial Intelligence 36(9):9413–9421.Crossref, Google Scholar
• [62] Pinkus A (1999) Approximation theory of the MLP model in neural networks. Acta Numer. 8:143–195.Crossref, Google Scholar
• [63] Salhab R, Malhamé R, Ny JL (2016) A dynamic collective choice model with an advertiser. 2016 IEEE 55th Conf. Decision Control (CDC) (IEEE, Piscataway, NJ), 6098–6104.Google Scholar
• [64] Salhab R, Le Ny J, Malhamé RP, Zaccour G (2022) Dynamic marketing policies with rating-sensitive consumers: A mean-field games approach. Eur. J. Oper. Res. 299(3):1079–1093.Crossref, Google Scholar
• [65] Sannikov Y (2008) A continuous-time version of the principal: Agent problem. Rev. Econom. Stud. 75(3):957–984.Crossref, Google Scholar
• [66] Sannikov Y (2013) Contracts: The theory of dynamic principal-agent relationships and the continuous-time approach. Acemoglu D, Arellano M, Dekel E, eds. Advances in Economics and Econometrics: Tenth World Congress, Econometric Society Monographs (Cambridge University Press, Cambridge, UK), 89–124.Crossref, Google Scholar
• [67] Sen N, Caines PE (2016) Mean field game theory with a partially observed major agent. SIAM J. Control Optim. 54(6):3174–3224.Crossref, Google Scholar
• [68] Wang BC (2024) Leader–follower mean field LQ games: A direct method. Asian J. Control 26(2):617–625.Crossref, Google Scholar
• [69] Yang X, Huang M (2021) Linear quadratic mean field Stackelberg games: Master equations and time consistent feedback strategies. 2021 60th IEEE Conf. Decision Control (CDC) (IEEE Press, Austin, TX), 171–176.Google Scholar