Abstract | ||
---|---|---|
In this paper, we study a class of discrete-time mean-field games under the infinite-horizon risk-sensitive discounted-cost optimality criterion. Risk-sensitivity is introduced for each agent (player) via an exponential utility function. In this game model, each agent is coupled with the rest of the population through the empirical distribution of the states, which affects both the agentu0027s individual cost and its state dynamics. Under mild assumptions, we establish the existence of a mean-field equilibrium in the infinite-population limit as the number of agents ($N$) goes to infinity, and then show that the policy obtained from the mean-field equilibrium constitutes an approximate Nash equilibrium when $N$ is sufficiently large. |
Year | Venue | Field |
---|---|---|
2018 | arXiv: Optimization and Control | Applied mathematics,Population,Mathematical optimization,Empirical distribution function,Optimality criterion,Infinity,Mean field theory,Exponential utility,Discrete time and continuous time,Nash equilibrium,Mathematics |
DocType | Volume | Citations |
Journal | abs/1808.03929 | 1 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Naci Saldi | 1 | 29 | 10.27 |
Tamer Başar | 2 | 10 | 6.44 |
Maxim Raginsky | 3 | 771 | 60.65 |