Q-learning in regularized mean-field games

DOI10.1007/s13235-022-00450-2zbMath1519.91032arXiv2003.12151OpenAlexW3013079993MaRDI QIDQ6159509

Berkay Anahtarci, Can Deha Karıksız, Naci Saldi

Publication date: 20 June 2023

Published in: Dynamic Games and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2003.12151

zbMATH Keywords

Q-learningmean-field gamesdiscounted rewardregularized Markov decision processes

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Rationality and learning in game theory (91A26) Mean field games (aspects of game theory) (91A16)

Related Items (3)

Model-free mean-field reinforcement learning: mean-field MDP and mean-field Q-learning ⋮ Model-free policy iteration approach to NCE-based strategy design for linear quadratic Gaussian games ⋮ MF-OMO: An Optimization Formulation of Mean-Field Games

Cites Work

• Stationary anonymous sequential games with undiscounted rewards
• Gibbs measures and phase transitions.
• Discrete time, finite state space mean field games
• Mean field games
• Discrete-time ergodic mean-field games with average reward on compact spaces
• Value iteration algorithm for mean-field games
• Equilibria of dynamic games with many players: existence, approximation, and market structure
• Discrete time mean-field stochastic linear-quadratic optimal control problems
• Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
• Mean field games models -- a brief survey
• Concentration inequalities for dependent random variables via the martingale method
• Probabilistic Analysis of Mean-Field Games
• Robust mean field games for coupled Markov jump linear systems
• Risk-Sensitive Mean-Field Games
• Learning in Mean-Field Games
• Large-Population LQG Games Involving a Major Player: The Nash Certainty Equivalence Principle
• Markov--Nash Equilibria in Mean-Field Games with Discounted Cost
• Approximate Nash Equilibria in Partially Observed Stochastic Games with Mean-Field Interactions
• Robustness to Incorrect System Models in Stochastic Control
• Robustness to Incorrect Priors in Partially Observed Stochastic Control
• Large-Population Cost-Coupled LQG Problems With Nonuniform Agents: Individual-Mass Behavior and Decentralized $\varepsilon$-Nash Equilibria
• Mean Field Games and Mean Field Type Control Theory

This page was built for publication: Q-learning in regularized mean-field games