MyHu-RC / Direct-Policy-Search-for-H-inf-State-Feedback-Problem

This code generate the simulation results in our NeurIPS 2022 paper titled "Global Convergence of Direct Policy Search for State-Feedback H∞ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential"

Direct-Policy-Search-for-H-inf-State-Feedback-Problem

This project contains the codes for implementable variants of Goldstein's subgradient methods including Gradient Sampling (GS), Non-derivative Sampling (NS), Interpolated Normalized Gradient Descent (INGD) and Model-free NS methods.

The codes can be used to generate the simulation results in our NeurIPS 2022 paper titled "Global Convergence of Direct Policy Search for State-Feedback H∞ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential" https://arxiv.org/abs/2210.11577