Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning

DOI10.1007/s10994-010-5192-9zbMath1237.68142OpenAlexW1963523946MaRDI QIDQ413845

Michael A. Goodrich, Jacob W. Crandall

Publication date: 8 May 2012

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-010-5192-9

zbMATH Keywords

game theoryreinforcement learningmulti-agent learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Multistage and repeated games (91A20) Agent technology and artificial intelligence (68T42)

Related Items (1)

A distributed algorithm to obtain repeated games equilibria with discounting

Uses Software

• R-MAX
• AdaBoost.MH
• AWESOME

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• If multi-agent learning is the answer, what is the question?
• No regrets about no-regret
• Subjectivity and correlation in randomized strategies
• Evolutionarily stable strategies and game dynamics
• Evolving aspirations and cooperation
• Multiagent learning using a variable learning rate
• \({\mathcal Q}\)-learning
• Regret in the on-line decision problem
• AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents
• 10.1162/153244303765208377
• The Bargaining Problem
• The Evolution of Cooperation
• The Evolution of Conventions
• Stochastic Games

This page was built for publication: Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning