Learning with minimal information in continuous games - Archive ouverte HAL Access content directly
Journal Articles Theoretical Economics Year : 2020

Learning with minimal information in continuous games

(1) , (2) , (1)
1
2
Sebastian Bervoets
Mario Bravo
  • Function : Author
  • PersonId : 1067576
Mathieu Faure
  • Function : Author
  • PersonId : 942384

Abstract

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.

Dates and versions

hal-02534257 , version 1 (06-04-2020)

Identifiers

Cite

Sebastian Bervoets, Mario Bravo, Mathieu Faure. Learning with minimal information in continuous games. Theoretical Economics, 2020, 15 (4), pp.1471-1508. ⟨10.3982/TE3435⟩. ⟨hal-02534257⟩
33 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More