The possible and the impossible in multi-agent learning

DOI10.1016/j.artint.2006.10.015zbMath1168.68507OpenAlexW3125153207MaRDI QIDQ1028928

H. Peyton Young

Publication date: 9 July 2009

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.artint.2006.10.015

zbMATH Keywords

dynamicslearningequilibrium

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Rationality and learning in game theory (91A26)

Related Items (4)

Evolutionary game theory: a renaissance ⋮ Two ``little treasure games driven by unconditional regret ⋮ Completely uncoupled dynamics and Nash equilibria ⋮ Stubborn learning

Cites Work

• Unnamed Item
• Stochastic uncoupled dynamics and Nash equilibrium
• If multi-agent learning is the answer, what is the question?
• Strategically zero-sum games: The class of games whose completely mixed equilibria cannot be improved upon
• Bayesian learning in normal form games
• Three problems in learning mixed-strategy Nash equilibria
• Calibrated learning and correlated equilibrium
• Learning, hypothesis testing, and Nash equilibrium.
• Regret in the on-line decision problem
• Global Nash convergence of Foster and Young's regret testing
• Rational Learning Leads to Nash Equilibrium
• Merging of Opinions with Increasing Information
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• A general class of adaptive strategies

This page was built for publication: The possible and the impossible in multi-agent learning