Mixed $\mathcal{H}_2/\mathcal{H}_\infty$-Policy Learning Synthesis

Author name not available (Why is that?)

Publication date: 17 February 2023

Abstract: A robustly stabilizing optimal control policy in a model-free mixed

m a t h c a l H_{2} / m a t h c a l H_{i} n f t y

-control setting is here put forward for counterbalancing the slow convergence and non-robustness of traditional high-variance policy optimization (and by extension policy gradient) algorithms. Leveraging It^{o}'s stochastic differential calculus, we iteratively solve the system's continuous-time closed-loop generalized algebraic Riccati equation whilst updating its admissible controllers in a two-player, zero-sum differential game setting. Our new results are illustrated by learning-enabled control systems which gather previously disseminated results in this field in one holistic data-driven presentation with greater simplification, improvement, and clarity.

Has companion code repository: https://github.com/robotsorcerer/robust-design

This page was built for publication: Mixed $\mathcal{H}_2/\mathcal{H}_\infty$-Policy Learning Synthesis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6426790)