Reinforcement learning for non-stationary discrete-time linear-quadratic mean-field games in multiple populations

DOI10.1007/s13235-022-00448-wzbMath1519.91036OpenAlexW4229457042MaRDI QIDQ6159510

Erik Miehling, Tamer Başar, Muhammad Aneeq uz Zaman

Publication date: 20 June 2023

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

Full work available at URL: https://doi.org/10.1007/s13235-022-00448-w

zbMATH Keywords

mean-field gamesmulti-agent reinforcement learninglarge population games on networkszero-order stochastic optimization

Mathematics Subject Classification ID

Games involving graphs (91A43) Optimal stochastic control (93E20) Rationality and learning in game theory (91A26) Mean field games (aspects of game theory) (91A16)

Related Items

Special issue: multi-agent dynamic decision making and learning, A mean field game approach for a class of linear quadratic discrete choice problems with congestion avoidance

Cites Work

• Linear-quadratic mean field games
• Mean field games
• Consensus via multi-population robust mean-field games
• Value iteration algorithm for mean-field games
• Finite horizon mean field games on networks
• Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
• Stationary Mean Field Games Systems Defined on Networks
• Markov--Nash Equilibria in Mean-Field Games with Discounted Cost
• Mean field games: A toy model on an Erdös-Renyi graph.
• Large-Population Cost-Coupled LQG Problems With Nonuniform Agents: Individual-Mass Behavior and Decentralized $\varepsilon$-Nash Equilibria
• Opinion Dynamics in Social Networks through Mean-Field Games
• Probabilistic Theory of Mean Field Games with Applications II