Reinforcement learning for non-stationary discrete-time linear–quadratic mean-field games in multiple populations
Year of publication: |
2023
|
---|---|
Authors: | Zaman, Muhammad Aneeq uz ; Miehling, Erik ; Başar, Tamer |
Published in: |
Dynamic games and applications : DGA. - Boston : Birkhäuser, ISSN 2153-0793, ZDB-ID 2581474-6. - Vol. 13.2023, 1, p. 118-164
|
Subject: | Large population games on networks | Mean-field games | Multi-agent reinforcement learning | Zero-order stochastic optimization | Lernprozess | Learning process | Spieltheorie | Game theory | Agentenbasierte Modellierung | Agent-based modeling | Stochastischer Prozess | Stochastic process | Lernen | Learning |
-
Deep Q-learning for Nash equilibria : Nash-DQN
Casgrain, Philippe, (2022)
-
Model-based graph reinforcement learning for inductive traffic signal control
Devailly, François-Xavier, (2022)
-
Lee, Hyun-Rok, (2021)
- More ...
-
Asynchronous algorithms in non-cooperative games
Başar, Tamer, (1988)
-
Başar, Tamer, (1987)
-
Stochastic incentive problems with partial dynamic information and multiple levels of hierarchy
Başar, Tamer, (1989)
- More ...