English

Model-Free $\mu$-Synthesis: A Nonsmooth Optimization Perspective

Optimization and Control 2024-02-20 v1 Machine Learning

Abstract

In this paper, we revisit model-free policy search on an important robust control benchmark, namely μ\mu-synthesis. In the general output-feedback setting, there do not exist convex formulations for this problem, and hence global optimality guarantees are not expected. Apkarian (2011) presented a nonconvex nonsmooth policy optimization approach for this problem, and achieved state-of-the-art design results via using subgradient-based policy search algorithms which generate update directions in a model-based manner. Despite the lack of convexity and global optimality guarantees, these subgradient-based policy search methods have led to impressive numerical results in practice. Built upon such a policy optimization persepctive, our paper extends these subgradient-based search methods to a model-free setting. Specifically, we examine the effectiveness of two model-free policy optimization strategies: the model-free non-derivative sampling method and the zeroth-order policy search with uniform smoothing. We performed an extensive numerical study to demonstrate that both methods consistently replicate the design outcomes achieved by their model-based counterparts. Additionally, we provide some theoretical justifications showing that convergence guarantees to stationary points can be established for our model-free μ\mu-synthesis under some assumptions related to the coerciveness of the cost function. Overall, our results demonstrate that derivative-free policy optimization offers a competitive and viable approach for solving general output-feedback μ\mu-synthesis problems in the model-free setting.

Keywords

Cite

@article{arxiv.2402.11654,
  title  = {Model-Free $\mu$-Synthesis: A Nonsmooth Optimization Perspective},
  author = {Darioush Keivan and Xingang Guo and Peter Seiler and Geir Dullerud and Bin Hu},
  journal= {arXiv preprint arXiv:2402.11654},
  year   = {2024}
}

Comments

Submitted to L4DC 2024

R2 v1 2026-06-28T14:52:26.155Z