Convergent learning algorithms for unknown reward games

DOI10.1137/120893501MaRDI QIDQ2862464zbMATH OpenOpenAlexFDO

Authors Archie C. Chapman, D. S. Leslie, Alex Rogers, Nicholas R. Jennings

Publication date 15 November 2013

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL https://eprints.soton.ac.uk/353067/1/SICON_089350R.pdf

zbMATH Keywords

distributed optimizationpotential gamesreinforcement learningstrong ergodicity

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Distributed algorithms (68W15) Noncooperative games (91A10) Rationality and learning in game theory (91A26)

Recommendations

• Convergent multiple-timescales reinforcement learning algorithms in normal form games
• On convergence rates of game theoretic reinforcement learning algorithms
• Individual Q-Learning in Normal Form Games
• On the convergence of reinforcement learning
• 10.1162/1532443041827880

Cited in

(23)

• Convergent multiple-timescales reinforcement learning algorithms in normal form games
• Stochastic learning in multi-agent optimization: communication and payoff-based approaches
• Learning in games with continuous action sets and unknown payoff functions
• On convergence rates of game theoretic reinforcement learning algorithms
• A strategic learning algorithm for state-based games
• A reinforcement learning scheme for the equilibrium of the in-vehicle route choice problem based on congestion game
• Analysis of Hannan consistent selection for Monte Carlo tree search in simultaneous move games
• AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents
• Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning
• Revisiting log-linear learning: asynchrony, completeness and payoff-based implementation
• scientific article; zbMATH DE number 2000817 (Why is no real title available?)
• scientific article; zbMATH DE number 2183056 (Why is no real title available?)
• scientific article; zbMATH DE number 1931819 (Why is no real title available?)
• 10.1162/1532443041827880
• Optimal Off-line Experimentation for Games
• GENERAL PROOF OF CONVERGENCE OF THE NASH-Q-LEARNING ALGORITHM
• Individual Q-Learning in Normal Form Games
• \(Q\)-learning in a stochastic Stackelberg game between an uninformed leader and a naive follower
• Evaluation and learning in two-player symmetric games via best and better responses
• A unified stochastic approximation framework for learning in games
• Learning Stationary Nash Equilibrium Policies in n-Player Stochastic Games with Independent Chains
• Hedging under uncertainty: regret minimization meets exponentially fast convergence
• Collusion by mistake: does algorithmic sophistication drive supra-competitive profits?

This page was built for publication: Convergent learning algorithms for unknown reward games

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2862464)