Revisiting log-linear learning: asynchrony, completeness and payoff-based implementation

DOI10.1016/j.geb.2012.03.006zbMath1239.91017OpenAlexW2024612830MaRDI QIDQ423755

Jeff S. Shamma, Jason R. Marden

Publication date: 4 June 2012

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

Full work available at URL: https://doi.org/10.1016/j.geb.2012.03.006

zbMATH Keywords

equilibrium selectiondistributed controlpotential games

Mathematics Subject Classification ID

Rationality and learning in game theory (91A26)

Related Items (20)

The price of anarchy and stability in general noisy best-response dynamics ⋮ Dynamics in atomic signaling games ⋮ Evolutionary game theory: a renaissance ⋮ State based potential games ⋮ Evaluation and learning in two-player symmetric games via best and better responses ⋮ Log-linear dynamics and local potential ⋮ Learning generalized Nash equilibria in monotone games: a hybrid adaptive extremum seeking control approach ⋮ Learning efficient Nash equilibria in distributed systems ⋮ Dynamics in near-potential games ⋮ Recent advances in optimization and game theoretic control for networked systems ⋮ Learning to play efficient coarse correlated equilibria ⋮ Amortized Analysis of Asynchronous Price Dynamics ⋮ Metastability of logit dynamics for coordination games ⋮ Robust stochastic stability ⋮ The logit-response dynamics ⋮ Transitions between equilibria in bilingual games under logit choice ⋮ Learning generalized Nash equilibria in multi-agent dynamical systems via extremum seeking control ⋮ An Adjusted Payoff-Based Procedure for Normal Form Games ⋮ Potential Games Are Necessary to Ensure Pure Nash Equilibria in Cost Sharing Games ⋮ Coalitional stochastic stability in games, networks and markets

Cites Work

• Unnamed Item
• Uncoupled automata and pure Nash equilibria
• Learning by trial and error
• If multi-agent learning is the answer, what is the question?
• Multi-agent learning for engineers
• The statistical mechanics of strategic interaction
• How noise matters.
• Potential games
• Fictitious play property for games with identical interests
• Best-response potential games
• The logit-response dynamics
• Global Nash convergence of Foster and Young's regret testing
• Waiting times and equilibrium selection
• Joint Strategy Fictitious Play With Inertia for Potential Games
• Routing without regret
• Payoff-Based Dynamics for Multiplayer Weakly Acyclic Games
• The Evolution of Conventions
• Stochastic Games

This page was built for publication: Revisiting log-linear learning: asynchrony, completeness and payoff-based implementation