Convergence of reinforcement learning to Nash equilibrium: A search-market experiment - INSU - Institut national des sciences de l'Univers Accéder directement au contenu
Article Dans Une Revue Physica A: Statistical Mechanics and its Applications Année : 2005

Convergence of reinforcement learning to Nash equilibrium: A search-market experiment

Eric Darmon
  • Fonction : Auteur
Roger Waldeck
  • Fonction : Auteur

Résumé

Since the introduction of Reinforcement Learning (RL) in Game Theory, a growing literature is concerned with the theoretical convergence of RL-driven outcomes towards Nash equilibrium. In this paper, we apply this issue to a search-theoretic framework (posted-price market) where sellers are confronted with a population of imperfectly informed buyers and take one decision per period (posted prices) with no direct interactions between sellers. We focus on three different scenarios with varying buyers’ characteristics. For each of these scenarios, we quantitatively and qualitatively test whether the learned variable (price strategy) converges to the Nash equilibrium. We also study the impact of the temperature parameter (defining the exploitation/exploration trade off) on these results.

Dates et versions

insu-03642991 , version 1 (15-04-2022)

Identifiants

Citer

Eric Darmon, Roger Waldeck. Convergence of reinforcement learning to Nash equilibrium: A search-market experiment. Physica A: Statistical Mechanics and its Applications, 2005, 355, pp.119-130. ⟨10.1016/j.physa.2005.02.074⟩. ⟨insu-03642991⟩

Collections

INSU
3 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More