Policy Optimization for $\mathcal{H}_2$ Linear Control with $\mathcal{H}_\infty$ Robustness Guarantee: Implicit Regularization and Global Convergence
From MaRDI portal
Publication:5163686
DOI10.1137/20M1347942zbMath1475.93036arXiv1910.09496MaRDI QIDQ5163686
Kaiqing Zhang, Tamer Başar, Bin Hu
Publication date: 5 November 2021
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1910.09496
Related Items (5)
A comparison of guaranteeing and Kalman filters ⋮ Decentralized nonconvex optimization with guaranteed privacy and accuracy ⋮ Minimum input design for direct data-driven property identification of unknown linear systems ⋮ Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence ⋮ Optimizing Static Linear Feedback: Gradient Method
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Mixed-norm \(H_ 2/H_{\infty}\) regulation and estimation: The discrete- time case
- Matrix differential calculus with applications to simple, Hadamard, and Kronecker products
- Existence and comparison theorems for algebraic Riccati equations for continuous- and discrete-time systems
- State-space formulae for all stabilizing controllers that satisfy an \(H_{\infty}\)-norm bound and relations to risk sensitivity
- Minimum entropy \(H_{\infty}\) control
- On the Kalman-Yakubovich-Popov lemma
- Mixed \({\mathcal H}_ 2/{\mathcal H}_{\infty}\) control for discrete-time systems via convex optimization
- Cubic regularization of Newton method and its global performance
- On the Complexity of Steepest Descent, Newton's and Regularized Newton's Methods for Nonconvex Unconstrained Optimization Problems
- Mixed $H_2/H_\infty$ Control via Nonsmooth Optimization
- A new CAD method and associated architectures for linear controllers
- Computational methods for parametric LQ problems--A survey
- LQG control with an H/sup infinity / performance bound: a Riccati equation approach
- Mixed H/sub 2//H/sub infinity / control: a convex optimization approach
- Linear Matrix Inequalities in System and Control Theory
- OnActor-Critic Algorithms
- An exact solution to general four-block discrete-time mixed ℋ/sub 2//ℋ/sub ∞/ problems via convex optimization
- Multiobjective H/sub 2//H/sub ∞/ control
- H/sub ∞/ design with pole placement constraints: an LMI approach
- Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
- Convergence and Sample Complexity of Gradient Methods for the Model-Free Linear–Quadratic Regulator Problem
- Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic differential games
- \(H^ \infty\)-optimal control and related minimax design problems. A dynamic game approach.
This page was built for publication: Policy Optimization for $\mathcal{H}_2$ Linear Control with $\mathcal{H}_\infty$ Robustness Guarantee: Implicit Regularization and Global Convergence
