Learning to play games in extensive form by valuation

DOI10.1016/j.jet.2004.09.004zbMath1116.91013MaRDI QIDQ2577520

Dov Samet, Philippe Jehiel

Publication date: 22 December 2005

Published in: Journal of Economic Theory (Search for Journal in Brave)

Full work available at URL: http://www.dklevine.com/archive/refs4391749000000000034.pdf

zbMATH Keywords

reinforcement learning; valuation; perfect equilibrium

Mathematics Subject Classification ID

91A18: Games in extensive form

91A26: Rationality and learning in game theory

Related Items

Introduction (to the special issue on: Economics and artificial intelligence), Modelling equilibrium play as governed by analogy and limited foresight, Learning across games, Existence of valuation equilibria when equilibrium strategies cannot differentiate between equal ties, If multi-agent learning is the answer, what is the question?, An economist's perspective on multi-agent learning

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Consistency and cautious fictitious play
• Evolving aspirations and cooperation
• Payoff assessments without probabilities: a simple dynamic model of choice
• An evolutionary analysis of backward and forward induction
• Learning through reinforcement and replicator dynamics
• Fictitious play in extensive form games
• Evolutionary dynamics and backward induction
• Learning aspiration in repeated games
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• Experience-weighted Attraction Learning in Normal Form Games
• Case-Based Decision Theory
• Self-Confirming Equilibrium