Skip to Main content Skip to Navigation
Journal articles

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

Abstract : 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.
Document type :
Journal articles
Complete list of metadata

https://hal-insu.archives-ouvertes.fr/insu-03642991
Contributor : Nathalie POTHIER Connect in order to contact the contributor
Submitted on : Friday, April 15, 2022 - 1:51:59 PM
Last modification on : Monday, May 9, 2022 - 3:27:46 AM

Links full text

Identifiers

Collections

Citation

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⟩

Share

Metrics

Record views

4