2 papers
math.OC2025
A Policy Gradient Framework for Stochastic Optimal Control Problems with Global Convergence Guarantee
Mo Zhou, Jianfeng Lu
We consider policy gradient methods for stochastic optimal control problem in continuous time. In particular, we analyze the gradient flow for the control, viewed as a continuous t…
math.OC2025
Solving Time-Continuous Stochastic Optimal Control Problems: Algorithm Design and Convergence Analysis of Actor-Critic Flow
Mo Zhou, Jianfeng Lu
We propose an actor-critic framework to solve the time-continuous stochastic optimal control problem. A least square temporal difference method is applied to compute the value func…