Learning efficient Nash equilibria in distributed systems

DOI10.1016/j.geb.2012.02.017zbMath1239.91018MaRDI QIDQ423765

H. Peyton Young, Bary S. R. Pradelski

Publication date: 4 June 2012

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

Full work available at URL: https://ora.ox.ac.uk/objects/uuid:c492c12a-0b1a-4290-9750-65376b6c2ab6

zbMATH Keywords

equilibrium selection; stochastic stability; distributed control; completely uncoupled learning

Mathematics Subject Classification ID

91A26: Rationality and learning in game theory

Related Items

Learning Equilibria of a Stochastic Game on Gaussian Interference Channels with Incomplete Information, A behavioral study of ``noise in coordination games, Evolutionary dynamics and equitable core selection in assignment games, The price of anarchy and stability in general noisy best-response dynamics, Conventional contracts, intentional behavior and logit choice: equality without symmetry, Core stability and core selection in a decentralized labor matching market, Evolutionary game theory: a renaissance, Selecting efficient correlated equilibria through distributed learning, Learning to play efficient coarse correlated equilibria, State based potential games, A strategic learning algorithm for state-based games, The evolution of conventions under condition-dependent mistakes, Agency, potential and contagion

Cites Work

• Revisiting log-linear learning: asynchrony, completeness and payoff-based implementation
• Uncoupled automata and pure Nash equilibria
• Average testing and Pareto efficiency
• Stochastic uncoupled dynamics and Nash equilibrium
• How long to equilibrium? The communication complexity of uncoupled equilibrium procedures
• Learning by trial and error
• Multi-agent learning for engineers
• Evolving aspirations and cooperation
• The statistical mechanics of strategic interaction
• How noise matters.
• Learning, hypothesis testing, and Nash equilibrium.
• Regret-based continuous-time dynamics.
• Multiagent learning using a variable learning rate
• The statistical mechanics of best-response strategy revision
• Global Nash convergence of Foster and Young's regret testing
• Evolutionary Implementation and Congestion Pricing
• Joint Strategy Fictitious Play With Inertia for Potential Games
• Achieving Pareto Optimality Through Distributed Learning
• Algorithms, games, and the internet
• Payoff-Based Dynamics for Multiplayer Weakly Acyclic Games
• Distributed Random Access Algorithm: Scheduling and Congestion Control
• Learning, Mutation, and Long Run Equilibria in Games
• The Evolution of Conventions
• Unnamed Item