UCSD

Mechanical and Aerospace Engineering

• Home
• Publications
• Group
• Teaching
• Software
• Lab

---

Equilibria of fully decentralized learning in networked systems
Y. Jiang, W. Cui, B. Zhang, J. Cortés
Conference on Learning for Dynamics and Control, Philadelphia, Pennsylvania, 2023, Proceedings of Machine Learning Research, volume 211, pp. 333-345

Abstract

Existing settings of decentralized learning either require players to have full information or the system to have certain special structure that may be hard to check and hinder their applicability to practical systems. To overcome this, we identify a structure that is simple to check for linear dynamical system, where each player learns in fully decentralized fashion to minimize its cost. We establish the existence of pure Nash equilibria in the resulting noncooperative game. We conjecture that the Nash equilibrium is unique provided that the system satisfies an additional requirement on its structure. We also introduce a decentralized mechanism based on projected gradient descent to have agents learn the Nash equilibria. Simulations on a 5-player game validate our results.

pdf

Mechanical and Aerospace Engineering, University of California, San Diego
9500 Gilman Dr, La Jolla, California, 92093-0411

Ph: 1-858-822-7930
Fax: 1-858-822-3107

cortes at ucsd.edu
Skype id: jorgilliyo