Risk-sensitive mean field stochastic differential games

Abstract In this paper, we study a class of risk-sensitive mean-field stochastic differential games. Under regularity assumptions, we use results from standard risk-sensitive differential game theory to show that the mean-field value of the exponentiated cost functional coincides with the value function of a Hamilton-Jacobi-Bellman-Fleming (HJBF) equation with an additional quadratic term. We provide an explicit solution of the mean-field best response when the instantaneous cost functions are log-quadratic and the state dynamics are affine in the control. An equivalent mean-field risk-neutral problem is formulated and the corresponding mean-field equilibria are characterized in terms of backward-forward macroscopic McKean-Vlasov equations, Fokker-Planck-Kolmogorov equations and HJBF equations.

[1]  Rhodes,et al.  Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic differential games , 1973 .

[2]  P. Whittle.  Risk-sensitive linear/quadratic/gaussian control , 1981, Advances in Applied Probability.

[3]  A. Bensoussan,et al.  Optimal control of partially observable stochastic systems with an exponential-of-integral performance index , 1985 .

[4]  R. Rosenthal,et al.  Anonymous sequential games , 1988 .

[5]  D. Bernhardt,et al.  Anonymous sequential games with aggregate uncertainty , 1992 .

[6]  T. Başar,et al.  Model simplification and optimal control of stochastic singularly perturbed systems under exponentiated quadratic cost , 1994, Proceedings of 1994 33rd IEEE Conference on Decision and Control.

[7]  T. Başar.  Nash Equilibria of Risk-Sensitive Nonlinear Stochastic Differential Games , 1999 .

[8]  P. Caines,et al.  Individual and mass behaviour in large population stochastic wireless power control problems: centralized and Nash equilibrium solutions , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[9]  Benjamin Van Roy,et al.  Oblivious Equilibrium: A Mean Field Approximation for Large-Scale Dynamic Games , 2005, NIPS.

[10]  Yasuo Tanabe,et al.  The propagation of chaos for interacting individuals in a large population , 2006, Math. Soc. Sci..

[11]  P. Lions,et al.  Mean field games , 2007 .

[12]  Minyi Huang,et al.  Large-Population Cost-Coupled LQG Problems With Nonuniform Agents: Individual-Mass Behavior and Decentralized $\varepsilon$-Nash Equilibria , 2007, IEEE Transactions on Automatic Control.

[13]  Andrea J. Goldsmith,et al.  Oblivious equilibrium for large-scale stochastic games with unbounded costs , 2008, 2008 47th IEEE Conference on Decision and Control.

[14]  Thomas G. Kurtz,et al.  Macroscopic limits for stochastic partial differential equations of McKean–Vlasov type , 2008 .

[15]  Eitan Altman,et al.  Mean field asymptotics of Markov Decision Evolutionary Games and teams , 2009, 2009 International Conference on Game Theory for Networks.

[16]  Sean P. Meyn,et al.  Synchronization of Coupled Oscillators is a Game , 2010, IEEE Transactions on Automatic Control.

[17]  Hamidou Tembine,et al.  Joint power control-allocation for green cognitive wireless networks using mean field theory , 2010, 2010 Proceedings of the Fifth International Conference on Cognitive Radio Oriented Wireless Networks and Communications.

[18]  Olivier Guéant,et al.  Mean Field Games and Applications , 2011 .

[19]  Hamidou Tembine,et al.  Mean field stochastic games: Convergence, Q/H-learning and optimality , 2011, Proceedings of the 2011 American Control Conference.