English

Multi-Agent Reinforcement Learning in Cournot Games

Optimization and Control 2020-09-15 v1 Computer Science and Game Theory Machine Learning Multiagent Systems Systems and Control Systems and Control

Abstract

In this work, we study the interaction of strategic agents in continuous action Cournot games with limited information feedback. Cournot game is the essential market model for many socio-economic systems where agents learn and compete without the full knowledge of the system or each other. We consider the dynamics of the policy gradient algorithm, which is a widely adopted continuous control reinforcement learning algorithm, in concave Cournot games. We prove the convergence of policy gradient dynamics to the Nash equilibrium when the price function is linear or the number of agents is two. This is the first result (to the best of our knowledge) on the convergence property of learning algorithms with continuous action spaces that do not fall in the no-regret class.

Keywords

Cite

@article{arxiv.2009.06224,
  title  = {Multi-Agent Reinforcement Learning in Cournot Games},
  author = {Yuanyuan Shi and Baosen Zhang},
  journal= {arXiv preprint arXiv:2009.06224},
  year   = {2020}
}

Comments

IEEE Conference on Decision and Control (CDC), 2020

R2 v1 2026-06-23T18:30:45.581Z