2 papers
math.OC2024
On the Convergence of Projected Policy Gradient for Any Constant Step Sizes
Jiacai Liu, Wenye Li, Dachao Lin +2
Projected policy gradient (PPG) is a basic policy optimization method in reinforcement learning. Given access to exact policy evaluations, previous studies have established the sub…
math.OC2024
Anderson Acceleration Without Restart: A Novel Method with -Step Super Quadratic Convergence Rate
Haishan Ye, Dachao Lin, Xiangyu Chang +1
In this paper, we propose a novel Anderson's acceleration method to solve nonlinear equations, which does \emph{not} require a restart strategy to achieve numerical stability. We p…