pith. sign in

arxiv: 2604.21641 · v1 · submitted 2026-04-23 · 🧮 math.OC

Robust mean field control: stochastic maximum principle and variational mean field games

Fran\c{c}ois Delarue (UniCA) , Pierre Lavigne (UniCA) This is my paper

Pith reviewed 2026-05-09 21:14 UTC · model grok-4.3

classification 🧮 math.OC
keywords robust mean field controlstochastic maximum principlevariational mean field gamesmin-max formulationexistence and uniquenessconvexity-concavityentropic costambiguity
0
0 comments X

The pith

Robust mean field control problems admit unique solutions and a stochastic maximum principle under convexity-concavity conditions.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper considers robust control problems cast as min-max games in which a central planner seeks to minimize a cost that may depend on the empirical distribution of states, while Nature chooses the worst-case realizations subject to an entropic penalty. Existence and uniqueness of solutions are proven when the running and terminal costs, as well as the interaction functions, satisfy appropriate convexity-concavity conditions. From the optimality conditions, a stochastic maximum principle is derived that characterizes the optimal controls. The same min-max approach is used to formulate and solve robust variational mean field games in which the interaction is ambiguous, again yielding existence and uniqueness.

Core claim

In this work, a class of robust mean field control problems is introduced in which the principal agent, acting as a central planner, faces an adversarial Nature that selects outcomes least favorable to the agent at an entropic cost. The agent's cost is a nonlinear function of all possible realizations, covering the mean-field case where dependence is on the state distribution. Under suitable assumptions including convexity-concavity conditions, existence and uniqueness of solutions are established and a stochastic maximum principle is derived. The framework is extended to robust variational mean field games with ambiguity in the interaction term, for which existence and uniqueness are also

What carries the argument

The min-max robust formulation between the central planner and Nature, which enables the derivation of the stochastic maximum principle for characterizing solutions in the mean field control and game settings.

If this is right

  • Existence and uniqueness of solutions hold for the robust mean field control problems.
  • The stochastic maximum principle provides a characterization of the optimal controls.
  • Existence and uniqueness of solutions hold for the robust variational mean field games with ambiguous interactions.
  • The nonlinear cost can depend on the distribution of states in the mean field regime.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The derived stochastic maximum principle may be used to obtain necessary conditions for optimality in related stochastic control problems with ambiguity.
  • This min-max approach with entropic cost offers a specific way to model robustness that could be compared to other ambiguity sets in future work.

Load-bearing premise

Suitable convexity-concavity conditions on the cost and interaction functions are required for the well-posedness of the min-max problems.

What would settle it

Constructing a cost function that violates the convexity-concavity conditions and demonstrating that the corresponding min-max robust control problem fails to have a unique solution.

read the original abstract

We introduce a class of robust control problems formulated in min-max form, in which the principal agent is viewed as a central planner facing Nature. The agent's cost is a nonlinear function of all its possible realizations, encompassing in particular the mean field regime where the cost depends on the distribution of the states. In parallel, Nature favors the occurrence of outcomes that are least favorable to the agent, at an entropic cost. We establish existence and uniqueness of solutions under appropriate assumptions, including suitable convexity-concavity conditions, and derive a related stochastic maximum principle. We further address a corresponding class of robust variational mean field games in which the interaction term is subject to ambiguity, and prove existence and uniqueness of solutions.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 3 minor

Summary. The paper introduces robust mean-field control problems cast as min-max games between a central planner (agent) and Nature, where the agent's cost is nonlinear in the state distribution (including mean-field dependence) and Nature's adversarial choices are penalized by relative entropy. Under convexity-concavity assumptions on the cost and interaction functions together with standard well-posedness conditions, the authors prove existence and uniqueness of solutions and derive a stochastic maximum principle. They then treat the corresponding class of robust variational mean-field games with ambiguity in the interaction term and likewise establish existence and uniqueness.

Significance. If the derivations hold, the work supplies a rigorous min-max formulation and associated stochastic maximum principle for robust mean-field control and games, extending classical stochastic control techniques to settings with distributional ambiguity. The explicit convexity-concavity hypotheses and entropic penalization are standard structural assumptions in robust control literature; the resulting characterization via the stochastic maximum principle offers a concrete tool for optimality conditions in large-population systems subject to model uncertainty.

major comments (2)
  1. [§3.2, Theorem 3.4] §3.2, Theorem 3.4 (stochastic maximum principle): the derivation of the adjoint equation and the verification that the candidate control satisfies the necessary condition appear to rely on an interchange of differentiation and expectation that is justified only under the stated Lipschitz and growth conditions; a brief remark on why the dominated-convergence argument carries over to the mean-field measure dependence would strengthen the claim.
  2. [§4.1, Assumption 4.2] §4.1, Assumption 4.2 (convexity-concavity of the interaction functional): the paper asserts that this condition guarantees uniqueness of the robust equilibrium, yet the proof sketch invokes a strict monotonicity argument that seems to require the interaction term to be strictly concave in the measure variable; if the concavity is only weak, the uniqueness claim may reduce to existence of a set-valued solution.
minor comments (3)
  1. [§2.3] Notation: the symbol μ for the mean-field measure is overloaded between the state distribution and the control measure in §2.3; a clarifying sentence or distinct font would avoid confusion.
  2. [Introduction] References: the discussion of related robust MFG literature in the introduction omits the recent works on entropic regularization in mean-field games (e.g., the 2022–2023 papers on Schrödinger-bridge formulations); adding two or three key citations would better situate the contribution.
  3. [Figure 1] Figure 1 (schematic of the min-max problem): the arrow labels are too small for readability; enlarging the font or adding a caption that spells out the roles of agent and Nature would improve clarity.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the careful reading, positive evaluation, and constructive suggestions. The comments help clarify key technical points in the stochastic maximum principle and the uniqueness argument. We address each major comment below and will incorporate the necessary revisions and clarifications in the updated manuscript.

read point-by-point responses

  1. Referee: [§3.2, Theorem 3.4] §3.2, Theorem 3.4 (stochastic maximum principle): the derivation of the adjoint equation and the verification that the candidate control satisfies the necessary condition appear to rely on an interchange of differentiation and expectation that is justified only under the stated Lipschitz and growth conditions; a brief remark on why the dominated-convergence argument carries over to the mean-field measure dependence would strengthen the claim.

    Authors: We agree that an explicit remark on the justification for interchanging differentiation under the integral (with respect to both the probability measure and the mean-field distribution) would improve readability. Under the Lipschitz continuity and linear growth conditions stated in Assumption 3.1, the integrands arising from the mean-field dependence remain dominated by an integrable random variable uniformly in a neighborhood of the candidate control; the Wasserstein continuity of the cost and interaction functionals then ensures the domination carries over to the measure variable. We will insert a short paragraph immediately after the proof of Theorem 3.4 spelling out this dominated-convergence argument. revision: yes

  2. Referee: [§4.1, Assumption 4.2] §4.1, Assumption 4.2 (convexity-concavity of the interaction functional): the paper asserts that this condition guarantees uniqueness of the robust equilibrium, yet the proof sketch invokes a strict monotonicity argument that seems to require the interaction term to be strictly concave in the measure variable; if the concavity is only weak, the uniqueness claim may reduce to existence of a set-valued solution.

    Authors: We appreciate the referee’s observation on the distinction between weak and strict concavity. Assumption 4.2 is formulated so that the concavity in the measure variable is strict (owing to the relative-entropy penalization and the structure of the ambiguity set), which directly yields the strict monotonicity used in the uniqueness proof. Nevertheless, to eliminate any possible misinterpretation, we will revise the statement of Assumption 4.2 to make the strictness explicit and expand the uniqueness argument in Section 4.1 to show why the resulting equilibrium is single-valued rather than set-valued. revision: yes

Circularity Check

0 steps flagged

No significant circularity; results derived from standard min-max analysis under explicit assumptions

full rationale

The paper formulates a min-max robust control problem and a related variational MFG, then proves existence/uniqueness and derives a stochastic maximum principle under convexity-concavity and other well-posedness assumptions. These are structural hypotheses stated upfront rather than derived internally. No self-definitional reductions, fitted inputs renamed as predictions, or load-bearing self-citations appear in the abstract or stated claims. The derivation chain relies on standard stochastic control techniques applied to the given min-max formulation, remaining self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claims rest on domain assumptions of convexity-concavity for well-posedness of the min-max problems; no free parameters or invented entities are introduced in the abstract.

axioms (1)
  • domain assumption Suitable convexity-concavity conditions on the cost and interaction functions
    Invoked to guarantee existence and uniqueness of solutions to the robust control and game problems.

pith-pipeline@v0.9.0 · 5419 in / 1359 out tokens · 80299 ms · 2026-05-09T21:14:00.597040+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

98 extracted references · 98 canonical work pages

  1. [1]

    Achdou, G

    Y. Achdou, G. Carlier, Q. Petit, and D. Tonon. A simple city equilibrium modelwithanapplicationtoteleworking. AppliedMathematics&Optimization, 88(2):60, 2023. 109

    work page 2023

  2. [2]

    Aksamit and C

    A. Aksamit and C. Fontana. Martingale spaces and representations under absolutely continuous changes of probability. Electronic Communications in Probability, 24:1 – 13, 2019

    work page 2019

  3. [3]

    Alasseur, I

    C. Alasseur, I. B. Tahar, and A. Matoussi. An extended mean field game for storage in smart grids.Journal of Optimization Theory and Applications, 184(2):644–670, 2020

    work page 2020

  4. [4]

    Andersson and B

    D. Andersson and B. Djehiche. A maximum principle for sdes of mean-field type. Applied Mathematics & Optimization, 63:341–356, 2011

    work page 2011

  5. [5]

    Armenti, S

    Y. Armenti, S. Crépey, S. Drapeau, and A. Papapantoleon. Multivariate short- fall risk allocation and systemic risk.SIAM Journal on Financial Mathematics, 9(1):90–126, 2018

    work page 2018

  6. [6]

    Başar and P

    T. Başar and P. Bernhard.H ∞-optimal control and related minimax design problems. Systems & Control: Foundations & Applications. Birkhäuser Boston, Inc., Boston, MA, 1991. A dynamic game approach

    work page 1991

  7. [7]

    Barrieu and N

    P. Barrieu and N. E. Karoui. Chapter three. pricing, hedging, and designing derivatives with risk measures. In R. Carmona, editor, Indifference Pricing, Theory and Applications, pages 77–146. Princeton University Press, Princeton, 2008

    work page 2008

  8. [8]

    Bauso, H

    D. Bauso, H. Tembine, and T. Başar. Robust mean field games.Dynamic games and applications, 6(3):277–303, 2016

    work page 2016

  9. [9]

    Benamou, G

    J.-D. Benamou, G. Carlier, S. Di Marino, and L. Nenna. An entropy mini- mization approach to second-order variational mean-field games.Mathematical Models and Methods in Applied Sciences, 29(08):1553–1583, 2019

    work page 2019

  10. [10]

    Benamou, G

    J.-D. Benamou, G. Carlier, and F. Santambrogio. Variational mean field games. In Active Particles, Volume 1, pages 141–171. Springer, 2017

    work page 2017

  11. [11]

    Bensoussan, J

    A. Bensoussan, J. Frehse, P. Yam, et al.Mean field games and mean field type control theory, volume 101. Springer, 2013

    work page 2013

  12. [12]

    Bertucci, J.-M

    C. Bertucci, J.-M. Lasry, and P.-L. Lions. Some remarks on mean field games. Communications in Partial Differential Equations, 44(3):205–227, 2019

    work page 2019

  13. [13]

    Biagini, J.-P

    F. Biagini, J.-P. Fouque, M. Frittelli, and T. Meyer-Brandis. A unified approach to systemic risk measures via acceptance sets.MathematicalFinance, 29(1):329– 367, 2019

    work page 2019

  14. [14]

    J.-M. Bismut. Linear quadratic optimal stochastic control with random coeffi- cients. SIAM Journal on Control and Optimization, 14(3):419–444, 1976

    work page 1976

  15. [15]

    J. F. Bonnans.Convex and Stochastic Optimization. Springer, 2019

    work page 2019

  16. [16]

    J. F. Bonnans, S. Hadikhanloo, and L. Pfeiffer. Schauder estimates for a class of potential mean field games of controls.Applied Mathematics & Optimization, 83:1431–1464, 2021. 110

    work page 2021

  17. [17]

    J. F. Bonnans, P. Lavigne, and L. Pfeiffer. Discrete potential mean field games: duality and numerical resolution.Mathematical Programming, 202(1):241–278, 2023

    work page 2023

  18. [18]

    B. Bonnet. A pontryagin maximum principle in wasserstein spaces for con- strained optimal control problems.ESAIM: Control, Optimisation and Calculus of Variations, 25:52, 2019

    work page 2019

  19. [19]

    Bonnet and F

    B. Bonnet and F. Rossi. The pontryagin maximum principle in the wasserstein space. Calculus of Variationsand Partial DifferentialEquations, 58(1):11, 2019

    work page 2019

  20. [20]

    Bourdais, N

    T. Bourdais, N. Oudjane, and F. Russo. An entropy penalized approach for stochastic control problems.SIAM J. Control Optim., 64(1):363–386, 2026

    work page 2026

  21. [21]

    H. Brezis. Functional Analysis, Sobolev Spaces and Partial Differential Equations. Universitext. Springer New York, 2010

    work page 2010

  22. [23]

    Briand, B

    P. Briand, B. Delyon, Y. Hu, E. Pardoux, and L. Stoica. Lp solutions of backward stochastic differential equations. Stochastic Processes and their Applications, 108(1):109–129, 2003

    work page 2003

  23. [24]

    Briand and Y

    P. Briand and Y. Hu. BSDE with quadratic growth and unbounded terminal value. Probability Theory and Related Fields, 136(4):604–618, 2006

    work page 2006

  24. [25]

    Briand and Y

    P. Briand and Y. Hu. Quadratic BSDEs with convex generators and unbounded terminal conditions.Probability Theory and Related Fields, 141:543–567, 2008

    work page 2008

  25. [26]

    Briani and P

    A. Briani and P. Cardaliaguet. Stable solutions in potential mean field game systems. Nonlinear Differential Equations and Applications NoDEA, 25(1):1, 2018

    work page 2018

  26. [27]

    Buckdahn, B

    R. Buckdahn, B. Djehiche, and J. Li. A general stochastic maximum principle for sdes of mean-field type.Applied Mathematics & Optimization, 64(2):197– 216, 2011

    work page 2011

  27. [28]

    Buckdahn, J

    R. Buckdahn, J. Li, and J. Ma. A stochastic maximum principle for general mean-field systems.Applied Mathematics & Optimization, 74:507–534, 2016

    work page 2016

  28. [29]

    Budhiraja and P

    A. Budhiraja and P. Dupuis. Analysis and approximation of rare events. Representations and weak convergence methods, volume 94 ofProbab. Theory Stoch. Model. New York, NY: Springer, 2019

    work page 2019

  29. [30]

    Cardaliaguet, S

    P. Cardaliaguet, S. Daudin, J. Jackson, and P. E. Souganidis. An algebraic convergence rate for the optimal control of McKean–Vlasov dynamics.SIAM Journal on Control and Optimization, 61(6):3341–3369, 2023

    work page 2023

  30. [31]

    Cardaliaguet, F

    P. Cardaliaguet, F. Delarue, J.-M. Lasry, and P.-L. Lions.The master equation and the convergence problem in mean field games, volume 201 ofAnn. Math. Stud. Princeton, NJ: Princeton University Press, 2019. 111

    work page 2019

  31. [32]

    Cardaliaguet, P

    P. Cardaliaguet, P. J. Graber, A. Porretta, and D. Tonon. Second order mean field games with degenerate diffusion and local coupling.Nonlinear Differential Equations and Applications NoDEA, 22(5):1287–1317, 2015

    work page 2015

  32. [33]

    Cardaliaguet and C.-A

    P. Cardaliaguet and C.-A. Lehalle. Mean field game of controls and an applica- tion to trade crowding.Mathematics and Financial Economics, 12(3):335–363, 2018

    work page 2018

  33. [34]

    Carmona and F

    R. Carmona and F. Delarue. Forward-backward stochastic differential equa- tions and controlled McKean-Vlasov dynamics. The Annals of Probability, 43(5):2647–2700, 2015

    work page 2015

  34. [35]

    Carmona and F

    R. Carmona and F. Delarue. Probabilistic theory of mean field games with applications I. Mean field FBSDEs, control, and games, volume 83 ofProbab. Theory Stoch. Model. Cham: Springer, 2018

    work page 2018

  35. [36]

    Carmona and F

    R. Carmona and F. Delarue. Probabilistic theory of mean field games with applications II. Mean field games with common noise and master equations, volume 84 ofProbab. Theory Stoch. Model. Cham: Springer, 2018

    work page 2018

  36. [37]

    Carmona, F

    R. Carmona, F. Delarue, and D. Lacker. Mean field games with common noise. The Annals of Probability, 44(6):3740 – 3803, 2016

    work page 2016

  37. [38]

    C. Chen, G. Iyengar, and C. C. Moallemi. An axiomatic approach to systemic risk. Management Science, 59(6):1373–1388, 2013

    work page 2013

  38. [39]

    Chen and L

    Z. Chen and L. Epstein. Ambiguity, risk, and asset returns in continuous time. Econometrica, 70(4):1403–1443, 2002

    work page 2002

  39. [40]

    Cheng and S

    Z. Cheng and S. Jaimungal. Risk-averse mean field games: exploitability and non-asymptotic analysis. arXiv, 2301.06930, 2023

    work page arXiv 2023

  40. [41]

    Cheridito and T

    P. Cheridito and T. Li. Dual characterization of properties of risk measures on orlicz hearts. Mathematics and Financial Economics, 2(1):29–55, 2008

    work page 2008

  41. [42]

    Cheridito and T

    P. Cheridito and T. Li. Risk measures on orlicz hearts.Mathematical Finance: An International Journal of Mathematics, Statistics and Financial Economics, 19(2):189–214, 2009

    work page 2009

  42. [43]

    Chizat, G

    L. Chizat, G. Peyré, B. Schmitzer, and F. c.-X. Vialard. Unbalanced op- timal transport: dynamic and Kantorovich formulations. J. Funct. Anal., 274(11):3090–3123, 2018

    work page 2018

  43. [44]

    P. L. Combettes. Perspective functions: Properties, constructions, and exam- ples. Set-Valuedand VariationalAnalysis, 26(2):247–264, 2018

    work page 2018

  44. [45]

    S. Daudin. Optimal control of the fokker-planck equation under state constraints in the wasserstein space. Journal de Mathématiques Pures et Appliquées, 175:37–75, 2023

    work page 2023

  45. [46]

    Daudin, F

    S. Daudin, F. Delarue, and J. Jackson. On the optimal rate for the convergence problem in mean field control.Journal of Functional Analysis, 287(12):110660, 2024. 112

    work page 2024

  46. [47]

    de la Vallée Poussin

    C.-J. de la Vallée Poussin. Sur l’intégrale de lebesgue.Transactions of the American Mathematical Society, pages 435–501, 1915

    work page 1915

  47. [48]

    Del Moral

    P. Del Moral. Feynman-Kac formulae. Probability and its Applications (New York). Springer-Verlag, New York, 2004

    work page 2004

  48. [49]

    Delarue and P

    F. Delarue and P. Lavigne. Robust mean-field games under entropy-based un- certainty. HAL, (hal-05556781v1), 2026

    work page 2026

  49. [50]

    Delbaen, Y

    F. Delbaen, Y. Hu, and A. Richou. On the uniqueness of solutions to quadratic BSDEs with convex generators and unbounded terminal conditions.Annales de l’I.H.P.Probabilités et statistiques, 47(2):559–574, 2011

    work page 2011

  50. [51]

    Dellacherie and P.-A

    C. Dellacherie and P.-A. Meyer. Probabilities and potential, volume 29 of North-Holland Mathematics Studies. North-Holland Publishing Co., Amsterdam-New York, 1978

    work page 1978

  51. [52]

    Dellacherie and P.-A

    C. Dellacherie and P.-A. Meyer.Probabilities and potential. B, volume 72 of North-Holland Mathematics Studies. North-Holland Publishing Co., Amster- dam, 1982

    work page 1982

  52. [53]

    M. F. Djete, D. Possamaï, and X. Tan. Mckean–Vlasov optimal control: limit theory and equivalence between different formulations.Mathematics of Operations Research, 47(4):2891–2930, 2022

    work page 2022

  53. [54]

    Dunford and J

    N. Dunford and J. T. Schwartz.Linear operators, part 1: general theory, vol- ume 10. John Wiley & Sons, 1988

    work page 1988

  54. [55]

    Dupuis and R

    P. Dupuis and R. S. Ellis.A weak convergence approach to the theory of large deviations. Wiley Ser. Probab. Stat. Chichester: John Wiley & Sons, 1997

    work page 1997

  55. [56]

    Escribe, J

    C. Escribe, J. Garnier, and E. Gobet. A mean field game model for renewable investment under long-term uncertainty and risk aversion.Dynamic Games and Applications, 14(5):1093–1130, 2024

    work page 2024

  56. [57]

    Féron, P

    O. Féron, P. Tankov, and L. Tinsi. Price formation and optimal trading in intraday electricity markets. In Network Games, Control and Optimization: 10thInternationalConference, NetGCooP 2020, France,September22–24,2021, Proceedings 10, pages 294–305. Springer, 2021

    work page 2020

  57. [58]

    Fleming and S

    W. Fleming and S. Sheu. Risk-sensitive control and an optimal investment model II. The Annals of Applied Probability, 12(2):730–767, 2002

    work page 2002

  58. [59]

    Frédéric Bonnans, P

    J. Frédéric Bonnans, P. Lavigne, and L. Pfeiffer. Discrete-time mean field games with risk-averse agents. ESAIM: Control, Optimisation and Calculus of Variations, 27:44, 2021

    work page 2021

  59. [60]

    A. Fromm. Theory and applications of decoupling fields for forward-backward stochastic differential equations. PhD thesis, Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät II, 2015

    work page 2015

  60. [61]

    P. J. Graber and C. Mouzouni. Variational mean field games for market com- petition. In PDE models for multi-agent phenomena, pages 93–114. Springer, 2018. 113

    work page 2018

  61. [62]

    Weaksolutionsforpotentialmeanfield games of controls.Nonlinear Differential Equations and Applications NoDEA, 28(5):1–34, 2021

    P.J.Graber, A.Mullenix, andL.Pfeiffer. Weaksolutionsforpotentialmeanfield games of controls.Nonlinear Differential Equations and Applications NoDEA, 28(5):1–34, 2021

    work page 2021

  62. [63]

    Robustcontrolandmodeluncertainty

    L.P.HansenandT.J.Sargent. Robustcontrolandmodeluncertainty. American Economic Review, 91(2):60–66, 2001

    work page 2001

  63. [64]

    U. G. Haussmann and J.-P. Lepeltier. On the existence of optimal controls. SIAM Journal on Control and Optimization, 28(4):851–902, 1990

    work page 1990

  64. [65]

    M. Hu. Stochastic global maximum principle for optimization with recursive utilities. Probability,Uncertainty and Quantitative Risk, 2:1–20, 2017

    work page 2017

  65. [66]

    M. Hu, S. Ji, and R. Xu. A global stochastic maximum principle for forward- backward stochastic control systems with quadratic generators.SIAM Journal on Control and Optimization, 60(3):1791–1818, 2022

    work page 2022

  66. [67]

    Huang, P

    M. Huang, P. E. Caines, and R. P. Malhamé. Large-population cost-coupled LQG problems with nonuniform agents: individual-mass behavior and decen- tralized ε-nash equilibria.IEEE transactions on automatic control, 52(9):1560– 1571, 2007

    work page 2007

  67. [68]

    J. Jackson. On quasilinear parabolic systems and FBSDEs of quadratic growth. The Annals of Applied Probability, 34(1A):357–387, 2024

    work page 2024

  68. [69]

    Kobeissi, I

    Z. Kobeissi, I. Mazari-Fouquer, and D. Ruiz-Balet. The tragedy of the commons: A Mean-Field Game approach to the reversal of travelling waves.Nonlinearity, 37(11):115010, 2024

    work page 2024

  69. [70]

    Kobylanski

    M. Kobylanski. Backward stochastic differential equations and partial differen- tial equations with quadratic growth.The Annals of Probability, 28(2):558–602, 2000

    work page 2000

  70. [71]

    Kromer, L

    E. Kromer, L. Overbeck, and K. Zilch. Systemic risk measures on general mea- surable spaces. Mathematical Methods of Operations Research, 84:323–357, 2016

    work page 2016

  71. [72]

    H. J. Kushner. On the stochastic maximum principle: Fixed time of control. Journal of Mathematical Analysis and Applications, 11:78–92, 1965

    work page 1965

  72. [73]

    D. Lacker. Limit theory for controlled McKean–Vlasov dynamics.SIAM Journal on Control and Optimization, 55(3):1641–1672, 2017

    work page 2017

  73. [74]

    Jeuxàchampmoyen.i–lecasstationnaire

    J.-M.LasryandP.-L.Lions. Jeuxàchampmoyen.i–lecasstationnaire. Comptes Rendus Mathématique, 343(9):619–625, 2006

    work page 2006

  74. [75]

    Lasry and P.-L

    J.-M. Lasry and P.-L. Lions. Jeux à champ moyen. ii–horizon fini et contrôle optimal. Comptes Rendus Mathématique, 343(10):679–684, 2006

    work page 2006

  75. [76]

    Laurière and O

    M. Laurière and O. Pironneau. Dynamic programming for mean-field type con- trol. Comptes Rendus Mathematique, 352(9):707–713, 2014

    work page 2014

  76. [77]

    Lavigne and P

    P. Lavigne and P. Tankov. Decarbonization of financial markets: a mean-field game approach.arXiv, 2301.09163, 2023. 114

    work page arXiv 2023

  77. [78]

    Luo and L

    P. Luo and L. Tangpi. Solvability of coupled fbsdes with diagonally quadratic generators. Stochastics and Dynamics, 17(06):1750043, 2017

    work page 2017

  78. [79]

    Moon and T

    J. Moon and T. Başar. Linear quadratic risk-sensitive and robust mean field games. IEEE Transactionson Automatic Control, 62(3):1062–1077, 2016

    work page 2016

  79. [80]

    Mouzouni

    C. Mouzouni. Topic in mean field games theory & applications in economics and quantitative finance. PhD thesis, Université de Lyon, 2019

    work page 2019

  80. [81]

    Nüsken and L

    N. Nüsken and L. Richter. Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffu- sions and measures on path space.Partial Differ. Equ. Appl., 2(4):Paper No. 48, 48, 2021

    work page 2021

Showing first 80 references.