Asymmetric Learning in Convex Games
- 24 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 71 (3) , 1962-1968
Abstract
This paper considers convex games involving multiple agents that aim to minimize their own cost functions using locally available information. A common assumption in the study of such games is that the agents are symmetric, meaning that they have access to the same type of information. Here we lift this assumption, which is often violated in practice, and instead consider asymmetric agents; specifically, we assume some agents have access to first-order gradient information and others have access to the zeroth-order oracles (cost function evaluations). We propose an asymmetric learning algorithm that combines the agent information mechanisms. We analyze the regret and Nash equilibrium convergence of this algorithm for convex and strongly monotone games, respectively. Specifically, we show that our algorithm always performs between pure first- and zeroth-order methods, and can match the performance of these two extremes by adjusting the number of agents with access to zeroth-order oracles. Therefore, our algorithm incorporates the pure first- and zeroth-order methods as special cases. We provide numerical experiments on a market problem for both deterministic and risk-averse games to demonstrate the performance of the proposed algorithm.Keywords
Funding Information
- Swedish Research Council under Distinguished Professor (2017-01078)
- Knut och Alice Wallenbergs Stiftelse
- Wallenberg Scholar Grant
- Swedish Strategic Research Foundation
- Air Force Office of Scientific Research (FA9550-19-1-0169)
- National Science Foundation (CNS-1932011)
- Wallenberg Scholar Grant, Swedish Strategic Research Foundation SUC-CESS
This publication has 25 references indexed in Scilit:
- DISH: A Distributed Hybrid Primal-Dual Optimization Framework to Utilize System Heterogeneity2022
- A Zeroth-Order Momentum Method for Risk-Averse Online Convex Games2022
- Improved Rates for Derivative Free Gradient Play in Strongly Monotone Games2022
- Equilibrium Tracking and Convergence in Dynamic Games2021
- Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms2021
- Dynamic Games in Cyber-Physical Security: An OverviewDynamic Games and Applications, 2019
- Learning in games with continuous action sets and unknown payoff functionsMathematical Programming, 2018
- Lectures on Convex Optimization2018
- Nash Equilibrium Seeking in Noncooperative GamesIEEE Transactions on Automatic Control, 2011
- Convex Optimization2004