Payoff performance of fictitious play

DOI10.3934/JDG.2014.1.621MaRDI QIDQ258745zbMATHOpenAlexFDO

Authors Georg Ostrovski, Sebastian van Strien

Publication date 10 March 2016

Published in Journal of Dynamics and Games (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1308.4049

zbMATH Keywords

Nash equilibriumcoarse correlated equilibriumfictitious playlearning algorithmspayoff performance

Mathematics Subject Classification ID

2-person games (91A05) Ordinary differential inclusions (34A60) Multistage and repeated games (91A20) Rationality and learning in game theory (91A26)

Abstract: We investigate how well continuous-time fictitious play in two-player games performs in terms of average payoff, particularly compared to Nash equilibrium payoff. We show that in many games, fictitious play outperforms Nash equilibrium on average or even at all times, and moreover that any game is linearly equivalent to one in which this is the case. Conversely, we provide conditions under which Nash equilibrium payoff dominates fictitious play payoff. A key step in our analysis is to show that fictitious play dynamics asymptotically converges the set of coarse correlated equilibria (a fact which is implicit in the literature).

Recommendations

• Fictitious play in networks
• The rate of convergence of continuous fictitious play
• On the rate of convergence of fictitious play

Cites work

• scientific article; zbMATH DE number 3122013 (Why is no real title available?)
• scientific article; zbMATH DE number 3128728 (Why is no real title available?)
• scientific article; zbMATH DE number 1233801 (Why is no real title available?)
• scientific article; zbMATH DE number 3205074 (Why is no real title available?)
• scientific article; zbMATH DE number 3069635 (Why is no real title available?)
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• A general class of adaptive strategies
• Adaptive Heuristics
• Belief affirming in learning processes
• Best response dynamics and socially stable strategies
• Best response equivalence
• Calibrated learning and correlated equilibrium
• Consistency and cautious fictitious play
• Correlated Equilibrium as an Expression of Bayesian Rationality
• Fictitious play in 3\(\times \)3 games: The transition between periodic and chaotic behaviour
• Fictitious play in \(2\times n\) games
• Fictitious play in \(3 \times 3\) games: chaos and dithering behaviour
• Fictitious play, Shapley polygons, and the replicator equations
• Hamiltonian flows with random-walk behaviour originating from zero-sum games and fictitious play
• Learning in games with strategic complementarities revisited
• On the convergence of fictitious play.
• On the rate of convergence of continuous-time fictitious play
• Piecewise linear Hamiltonian flows associated to zero-sum games: transition combinatorics and questions on ergodicity
• Social Stability and Equilibrium
• Strategically zero-sum games: The class of games whose completely mixed equilibria cannot be improved upon
• Subjectivity and correlation in randomized strategies
• Two more classes of games with the continuous-time fictitious play property
• �ber periodizit�tseigenschaften spieltheoretischer lernprozesse

Cited in

(3)

• Fictitious play in networks
• Regret-based continuous-time dynamics.
• No-regret dynamics and fictitious play

This page was built for publication: Payoff performance of fictitious play

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q258745)