A payoff-based learning procedure and its application to traffic games

DOI10.1016/j.geb.2008.11.012zbMath1244.91012OpenAlexW2087486726MaRDI QIDQ993787

Emerson Melo, Roberto Cominetti, Sylvain Sorin

Publication date: 20 September 2010

Published in: Games and Economic Behavior (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.geb.2008.11.012

zbMATH Keywords

learningcongestion gamesstochastic algorithmsgamesadaptive dynamics

Mathematics Subject Classification ID

Stochastic games, stochastic differential games (91A15) Traffic problems in operations research (90B20) Multistage and repeated games (91A20)

Related Items

On the robustness of learning in games with stochastically perturbed payoff observations ⋮ Penalty-Regulated Dynamics and Robust Learning Procedures in Games ⋮ Comparing human behavior models in repeated Stackelberg security games: an extended study ⋮ Bifurcation mechanism design -- from optimal flat taxes to better cancer treatments ⋮ ``Cap and trade for congestion control ⋮ An adaptive learning model with foregone payoff information ⋮ Learning and equilibrium transitions: stochastic stability in discounted stochastic fictitious play ⋮ Preface: Special issue in honor of the 60th birthday of Sylvain Sorin ⋮ A review of transport market modeling using game-theoretic principles ⋮ Securing infrastructure facilities: when does proactive defense help? ⋮ A generalization of quantal response equilibrium via perturbed utility ⋮ Convergence results on stochastic adaptive learning ⋮ TESTING THE QUANTAL RESPONSE HYPOTHESIS ⋮ Learning in Games via Reinforcement and Regularization ⋮ An Adjusted Payoff-Based Procedure for Normal Form Games ⋮ On the stability of an adaptive learning dynamics in traffic games ⋮ On the uniqueness of quantal response equilibria and its application to network games ⋮ Equilibrium routing under uncertainty ⋮ An adaptive learning model in coordination games

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A behavioral learning process in games
• Commuters route choice behaviour
• Calibrated learning and correlated equilibrium
• Learning through reinforcement and replicator dynamics
• On the convergence of reinforcement learning
• Potential games
• Mixed equilibria and dynamical systems arising from fictitious play in perturbed games
• Adaptive game playing using multiplicative weights
• Quantal response equilibria for normal form games
• Learning, information, and sorting in market entry games: theory and evidence
• A class of games possessing pure-strategy Nash equilibria
• An iterative method of solving a game
• Asymptotic calibration
• The Nonstochastic Multiarmed Bandit Problem
• Evolutionary Implementation and Congestion Pricing
• Day-To-Day Dynamic Network Disequilibria and Idealized Traveler Information Systems
• Dynamic Processes and Equilibrium in Transportation Networks: Towards a Unifying Theory
• Large Population Approximations of a General Stochastic Traffic Assignment Model
• Stochastic Approximations and Differential Inclusions
• Adaptive Heuristics
• On the Global Convergence of Stochastic Fictitious Play
• Potential games with continuous player sets