Payoff performance of fictitious play

DOI10.3934/JDG.2014.1.621zbMATH Open1332.91024arXiv1308.4049OpenAlexW2963864634MaRDI QIDQ258745FDOQ258745

Authors: Georg Ostrovski, Sebastian van Strien 

Publication date: 10 March 2016

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

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).

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

Recommendations

• On the approximation performance of fictitious play in finite games
• Fictitious play in networks
• The rate of convergence of continuous fictitious play
• On the approximation performance of fictitious play in finite games
• On the rate of convergence of fictitious play

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)

Cites Work

• Strategically zero-sum games: The class of games whose completely mixed equilibria cannot be improved upon
• Best response dynamics and socially stable strategies
• Subjectivity and correlation in randomized strategies
• Belief affirming in learning processes
• Calibrated learning and correlated equilibrium
• On the rate of convergence of continuous-time fictitious play
• Fictitious play in \(2\times n\) games
• Fictitious play, Shapley polygons, and the replicator equations
• Piecewise linear Hamiltonian flows associated to zero-sum games: transition combinatorics and questions on ergodicity
• On the convergence of fictitious play.
• Hamiltonian flows with random-walk behaviour originating from zero-sum games and fictitious play
• Title not available (Why is that?)
• Title not available (Why is that?)
• Social Stability and Equilibrium
• Correlated Equilibrium as an Expression of Bayesian Rationality
• Title not available (Why is that?)
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• Title not available (Why is that?)
• Adaptive Heuristics
• �ber periodizit�tseigenschaften spieltheoretischer lernprozesse
• Title not available (Why is that?)
• A general class of adaptive strategies
• Consistency and cautious fictitious play
• Best response equivalence
• Fictitious play in \(3 \times 3\) games: chaos and dithering behaviour
• Two more classes of games with the continuous-time fictitious play property
• Fictitious play in 3\(\times \)3 games: The transition between periodic and chaotic behaviour
• Learning in games with strategic complementarities revisited

Cited In (3)

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

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)