conference paper
Learning Nash Equilibria in Monotone Games
December 2019
2019 IEEE 58th Conference on Decision and Control (CDC)
We consider multi-agent decision making where each agent's cost function depends on all agents' strategies. We propose a distributed algorithm to learn a Nash equilibrium, whereby each agent uses only obtained values of her cost function at each joint played action, lacking any information of the functional form of her cost or other agents' costs or strategy sets. In contrast to past work where convergent algorithms required strong monotonicity, we prove algorithm convergence under mere monotonicity assumption. This significantly widens algorithm's applicability, such as to games with linear coupling constraints.
Type
conference paper
Author(s)
Tatarenko, Tatiana
Date Issued
2019-12
Publisher
Publisher place
Nice, France
Published in
2019 IEEE 58th Conference on Decision and Control (CDC)
ISBN of the book
978-1-72811-398-2
Start page
3104
End page
3109
Editorial or Peer reviewed
REVIEWED
Written at
OTHER
EPFL units
Event name | Event place | Event date |
Nice, France | 2019-12 | |
Available on Infoscience
December 1, 2021
Use this identifier to reference this record