An Adjusted Payoff-Based Procedure for Normal Form Games

DOI10.1287/moor.2016.0785zbMath1349.91062arXiv1106.5596OpenAlexW1625953579MaRDI QIDQ2833112

Mario Bravo

Publication date: 16 November 2016

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1106.5596

zbMATH Keywords

learningstochastic approximationadaptive dynamicsnormal form games

Mathematics Subject Classification ID

Noncooperative games (91A10) (n)-person games, (n>2) (91A06) Stochastic approximation (62L20) Stochastic learning and adaptive control (93E35) Rationality and learning in game theory (91A26) Multistage and repeated games (91A20)

Related Items

Penalty-Regulated Dynamics and Robust Learning Procedures in Games, Learning and equilibrium transitions: stochastic stability in discounted stochastic fictitious play, On the stability of an adaptive learning dynamics in traffic games

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Revisiting log-linear learning: asynchrony, completeness and payoff-based implementation
• A behavioral learning process in games
• Nonconvergence to unstable points in urn models and stochastic approximations
• A payoff-based learning procedure and its application to traffic games
• The statistical mechanics of strategic interaction
• Learning through reinforcement and replicator dynamics
• On the convergence of reinforcement learning
• Potential games
• Adaptive game playing using multiplicative weights
• Do stochastic algorithms avoid traps?
• The logit-response dynamics
• Learning in perturbed asymmetric games
• Urn Models, Replicator Processes, and Random Genetic Drift
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• Individual Q-Learning in Normal Form Games
• A Stochastic Approximation Method