Provably efficient reinforcement learning in decentralized general-sum Markov games

DOI10.1007/s13235-021-00420-0zbMath1519.91029arXiv2110.05682OpenAlexW3205079722MaRDI QIDQ6159512

Weichao Mao, Tamer Başar

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/2110.05682

zbMATH Keywords

reinforcement learningMarkov gamecoarse correlated equilibriumsample complexity

Mathematics Subject Classification ID

Stochastic games, stochastic differential games (91A15) Rationality and learning in game theory (91A26)

Related Items (1)

Special issue: multi-agent dynamic decision making and learning

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Strategically zero-sum games: The class of games whose completely mixed equilibria cannot be improved upon
• Scale-free online learning
• Stochastic networked control systems. Stabilization and optimization under information constraints
• Common Information Based Markov Perfect Equilibria for Stochastic Games With Asymmetric Information: Finite Games
• Settling the complexity of computing two-player Nash equilibria
• Correlated Equilibrium as an Expression of Bayesian Rationality
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• 10.1162/1532443041827880
• Superhuman AI for heads-up no-limit poker: Libratus beats top professionals
• The Complexity of Computing a Nash Equilibrium
• Decentralized Q-Learning for Stochastic Teams and Games
• Individual Q-Learning in Normal Form Games
• Decentralized Stochastic Control with Partial History Sharing: A Common Information Approach
• Prediction, Learning, and Games
• The Complexity of Decentralized Control of Markov Decision Processes
• Stochastic Games
• Computing correlated equilibria in multi-player games

This page was built for publication: Provably efficient reinforcement learning in decentralized general-sum Markov games