Markov-Nash equilibria in mean-field games with discounted cost
From MaRDI portal
(Redirected from Publication:4556905)
Abstract: In this paper, we consider discrete-time dynamic games of the mean-field type with a finite number of agents subject to an infinite-horizon discounted-cost optimality criterion. The state space of each agent is a locally compact Polish space. At each time, the agents are coupled through the empirical distribution of their states, which affects both the agents' individual costs and their state transition probabilities. We introduce a new solution concept of the Markov-Nash equilibrium, under which a policy is player-by-player optimal in the class of all Markov policies. Under mild assumptions, we demonstrate the existence of a mean-field equilibrium in the infinite-population limit , and then show that the policy obtained from the mean-field equilibrium is approximately Markov-Nash when the number of agents is sufficiently large.
Recommendations
- Approximate Markov-Nash equilibria for discrete-time risk-sensitive mean-field games
- Discrete-time average-cost mean-field games on Polish spaces
- Approximate Nash equilibria in partially observed stochastic games with mean-field interactions
- Mean field stochastic games: monotone costs and threshold policies
- On the rate of convergence for the mean-field approximation of controlled diffusions with large number of players
Cites work
- A note on semi-Markov perfect equilibria in discounted stochastic games
- Anonymous sequential games
- Convergence of Dynamic Programming Models
- Corrigendum to: ``Discounted stochastic games with no stationary Nash equilibrium: two examples
- Decentralized Convergence to Nash Equilibria in Constrained Deterministic Mean Field Control
- Discrete time mean-field stochastic linear-quadratic optimal control problems
- Discrete time, finite state space mean field games
- Equilibria of dynamic games with many players: existence, approximation, and market structure
- scientific article; zbMATH DE number 1325008 (Why is no real title available?)
- scientific article; zbMATH DE number 1354815 (Why is no real title available?)
- scientific article; zbMATH DE number 3245885 (Why is no real title available?)
- scientific article; zbMATH DE number 3320878 (Why is no real title available?)
- Infinite dimensional analysis. A hitchhiker's guide.
- Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
- Large-Population Cost-Coupled LQG Problems With Nonuniform Agents: Individual-Mass Behavior and Decentralized \varepsilon-Nash Equilibria
- Large-population LQG games involving a major player: the Nash certainty equivalence principle
- Linear Quadratic Risk-Sensitive and Robust Mean Field Games
- Long time results for a weakly interacting particle system in discrete time
- Markov Perfect Industry Dynamics With Many Firms
- Mean field game theory with a partially observed major agent
- Mean field games
- Mean field games and mean field type control theory
- Mean field games models -- a brief survey
- Mean Field LQG Control in Leader-Follower Stochastic Multi-Agent Systems: Likelihood Ratio Based Adaptation
- Measure theory. Vol. I and II
- Optimal Transport
- Probabilistic analysis of mean-field games
- Risk-Sensitive Mean-Field Games
- Robust mean field games
- Robust mean field games for coupled Markov jump linear systems
- Stationary almost Markov perfect equilibria in discounted stochastic games
- Stochastic optimal control. The discrete time case
- Synchronization of Coupled Oscillators is a Game
- Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
Cited in
(47)- Large deviations principle for discrete-time mean-field games
- A mean field approach for discounted zero-sum games in a class of systems of interacting objects
- Multi-agent reinforcement learning: a selective overview of theories and algorithms
- Discrete-time ergodic mean-field games with average reward on compact spaces
- Value iteration algorithm for mean-field games
- Connections between mean-field game and social welfare optimization
- Binary mean field stochastic games: stationary equilibria and comparative statics
- Mean field Markov decision processes
- Approximate Markov-Nash equilibria for discrete-time risk-sensitive mean-field games
- An approximate Nash equilibrium for pure jump Markov games of mean-field-type on continuous state space
- Discrete-time average-cost mean-field games on Polish spaces
- Exact and approximate Nash equilibria in discounted Markov stopping games with terminal redemption
- Discrete-time mean field games with risk-averse agents
- Mean-field controls with Q-learning for cooperative MARL: convergence and complexity analysis
- A Mean Field Game Approach to Equilibrium Pricing with Market Clearing Condition
- Mean field stochastic games: monotone costs and threshold policies
- Approximate Nash equilibria in partially observed stochastic games with mean-field interactions
- Robustness to incorrect system models in stochastic control
- An infinite-horizon mean field game of growth and capital accumulation: a Markov chain approximation numerical scheme and its challenges
- Risk-Sensitive Average Optimality for Discrete-Time Markov Decision Processes
- Extended Mean Field Games with Singular Controls
- Partially observed discrete-time risk-sensitive mean field games
- Stochastic Mitra-Wan forestry models analyzed as a mean field optimal control problem
- Q-learning in regularized mean-field games
- Reinforcement learning for non-stationary discrete-time linear-quadratic mean-field games in multiple populations
- MF-OMO: An Optimization Formulation of Mean-Field Games
- Adaptive mean field multi-agent reinforcement learning
- Actor-critic reinforcement learning algorithms for mean field games in continuous time, state and action spaces
- Hypergraphon mean field games
- Sequential decomposition of discrete-time mean-field games
- Infinite horizon average cost optimality criteria for mean-field control
- Multiple-population discrete-time mean field games with discounted and total payoffs: the existence of equilibria
- Conservation laws of mean field games equations with time discounting
- Learning with linear function approximations in mean-field control
- MF-OML: online mean-field reinforcement learning with occupation measures for large population games
- Finite approximations for mean-field type multi-agent control and their near optimality
- On time-inconsistency in mean-field games
- Statistical estimation of mean-field equilibria in a class of discounted mean-field games
- Nash equilibria of networked games with delayed coupling in the high population regime
- Mean-field games with finitely many players: independent learning and subjectivity
- Multiple-population discrete-time mean field games with discounted and total payoffs: approximation of games with finite populations
- Incentive designs for Stackelberg games with a large number of followers and their mean-field limits
- Time-varying discrete-time mean-field games under a discounted criterion
- Large population discounted zero-sum games with unknown disturbance distribution: a mean-field approach
- Markov perfect equilibria in discrete finite-player and mean-field games
- Erratum to: ``Markov-Nash equilibria in mean-field games with discounted cost
- Major-minor mean field game of stopping: an entropy regularization approach
This page was built for publication: Markov-Nash equilibria in mean-field games with discounted cost
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4556905)
