A Policy Gradient Framework for Stochastic Optimal Control Problems with Global Convergence Guarantee

Mo Zhou, Jianfeng Lu
2/11/2023
math.OCcs.LGeess.SY

No confident code implementation found for this paper.

Abstract

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 time limit of the policy gradient method. We prove the global convergence of the gradient flow and establish a convergence rate under some regularity assumptions. The main novelty in the analysis is the notion of local optimal control function, which is introduced to characterize the local optimality of the iterate.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Cite this paper

@article{zhou2023policy,
  title  = {A Policy Gradient Framework for Stochastic Optimal Control Problems with Global Convergence Guarantee},
  author = {Mo Zhou and Jianfeng Lu},
  year   = {2023},
  eprint = {2302.05816},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.05816v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.05816.svg)](https://codeofpaper.com/paper/2302.05816)

Discussion