On the stability of an adaptive learning dynamics in traffic games

DOI10.3934/jdg.2018017zbMath1422.91146arXiv1807.01256OpenAlexW2809832715MaRDI QIDQ2319665

Miguel A. Dumett, Roberto Cominetti

Publication date: 20 August 2019

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

Full work available at URL: https://arxiv.org/abs/1807.01256

zbMATH Keywords

stabilitydynamical systemscongestion gamesstochastic algorithmsRouth-Hurwitz criterionadaptive learning dynamicsrouting equilibrium

Mathematics Subject Classification ID

2-person games (91A05) Games involving graphs (91A43) Rationality and learning in game theory (91A26)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic approximation, cooperative dynamics and supermodular games
• A behavioral learning process in games
• Commuters route choice behaviour
• A payoff-based learning procedure and its application to traffic games
• Cooperative dynamics and Wardrop equilibria
• Nonlinear oscillations, dynamical systems, and bifurcations of vector fields
• Stochastic approximation algorithms with constant step size whose average is cooperative
• Calibrated learning and correlated equilibrium
• Learning through reinforcement and replicator dynamics
• Almost strict total positivity and a class of Hurwitz polynomials
• On the convergence of reinforcement learning
• Adaptive game playing using multiplicative weights
• Quantal response equilibria for normal form games
• A class of games possessing pure-strategy Nash equilibria
• An iterative method of solving a game
• An Adjusted Payoff-Based Procedure for Normal Form Games
• Learning in Bayesian Games with Binary Actions
• Systems of Ordinary Differential Equations Which Generate an Order Preserving Flow. A Survey of Results
• Asymptotic calibration
• Evolutionary Games and Population Dynamics
• Numerical Solution of Partial Differential Equations
• The Nonstochastic Multiarmed Bandit Problem
• Adaptive Heuristics
• On the Global Convergence of Stochastic Fictitious Play
• Totally positive matrices
• Elements of applied bifurcation theory