Online Learning of Nash Equilibria in Congestion Games

DOI10.1137/140980685zbMath1409.91013arXiv1408.0017OpenAlexW2094238774MaRDI QIDQ5252509

Alexandre M. Bayen, Benjamin Drighés, Walid Krichene

Publication date: 2 June 2015

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1408.0017

zbMATH Keywords

Nash equilibriaonline learningpopulation dynamicscongestion gamesregret minimization

Mathematics Subject Classification ID

Noncooperative games (91A10) Games with infinitely many players (91A07) Rationality and learning in game theory (91A26) Multistage and repeated games (91A20) Software, source code, etc. for problems pertaining to game theory, economics, and finance (91-04) Online algorithms; streaming algorithms (68W27)

Related Items (5)

Unnamed Item ⋮ Evolution of Mixed Strategies in Monotone Games ⋮ Adaptive constraint satisfaction for Markov decision process congestion games: application to transportation networks ⋮ Separation of learning and control for cyber-physical systems ⋮ Stochastic learning in multi-agent optimization: communication and payoff-based approaches

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The multi-armed bandit problem with covariates
• Exponentiated gradient versus gradient descent for linear predictors
• A concrete approach to classical analysis
• The weighted majority algorithm
• Adaptive game playing using multiplicative weights
• Stable games and their dynamics
• Population games, stable games, and passivity
• A class of games possessing pure-strategy Nash equilibria
• Non-cooperative games
• How bad is selfish routing?
• Adaptive routing with end-to-end feedback
• Weakly α-favourable measure spaces
• Multiplicative updates outperform generic no-regret learning in congestion games
• Routing without regret
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• Algorithms – ESA 2004
• Prediction, Learning, and Games
• Potential games with continuous player sets

This page was built for publication: Online Learning of Nash Equilibria in Congestion Games