Stability of Gradient Learning Dynamics in Continuous Games: Vector Action Spaces
Abstract
Towards characterizing the optimization landscape of games, this paper analyzes the stability of gradient-based dynamics near fixed points of two-player continuous games. We introduce the quadratic numerical range as a method to characterize the spectrum of game dynamics and prove the robustness of equilibria to variations in learning rates. By decomposing the game Jacobian into symmetric and skew-symmetric components, we assess the contribution of a vector field's potential and rotational components to the stability of differential Nash equilibria. Our results show that in zero-sum games, all Nash are stable and robust; in potential games, all stable points are Nash. For general-sum games, we provide a sufficient condition for instability. We conclude with a numerical example in which learning with timescale separation results in faster convergence.
Keywords
Cite
@article{arxiv.2011.05562,
title = {Stability of Gradient Learning Dynamics in Continuous Games: Vector Action Spaces},
author = {Benjamin J. Chasnov and Daniel Calderone and Behçet Açıkmeşe and Samuel A. Burden and Lillian J. Ratliff},
journal= {arXiv preprint arXiv:2011.05562},
year = {2021}
}
Comments
extension of arXiv:2011.03650 to vector action spaces. Submitted to IEEE L-CSS