Fiche du document
- handle: 10670/1.b1kmuc
- hal: hal-02534257
- ARXIV: 1806.11506
- doi: 10.3982/TE3435
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/arxiv/1806.11506
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/doi/10.3982/TE3435
Sujets proches
Amusements Children--Recreation Games for children Pastimes Primitive games Recreations Games, Primitive Children's gamesCiter ce document
Sebastian Bervoets et al., « Learning with minimal information in continuous games », HAL-SHS : économie et finance, ID : 10.3982/TE3435
Métriques
Partage / Export
Résumé
While payoff-based learning models are almost exclusively devised for finite action games, where players can test every action, it is harder to design such learning processes for continuous games. We construct a stochastic learning rule, designed for games with continuous action sets, which requires no sophistication from the players and is simple to implement: players update their actions according to variations in own payoff between current and previous action. We then analyze its behavior in several classes of continuous games and show that convergence to a stable Nash equilibrium is guaranteed in all games with strategic complements as well as in concave games, while convergence to Nash occurs in all locally ordinal potential games as soon as Nash equilibria are isolated.