Policy Gradient Methods for the Cost-Constrained LQR: Strong Duality and Global Convergence
- 1 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 70 (12) , 8414-8421
Abstract
No abstract availableAll Related Versions
Funding Information
- National Key R&D Program of China (2022ZD0116700)
- National Natural Science Foundation of China (62033006, 62325305)
This publication has 19 references indexed in Scilit:
- Infinite-horizon Risk-constrained Linear Quadratic Regulator with Average Cost2021
- Multi-objective $\mathcal {H}_2/\mathcal {H}_\infty $ Control Designs2021
- Risk-Constrained Linear-Quadratic Regulators2020
- Risk Averse Robust Adversarial Reinforcement Learning2019
- A General Safety Framework for Learning-Based Control in Uncertain Robotic SystemsIEEE Transactions on Automatic Control, 2018
- Chance-constrained dynamic programming with application to risk-aware robotic space explorationAutonomous Robots, 2015
- Subgradient Methods for Saddle-Point ProblemsJournal of Optimization Theory and Applications, 2009
- Stochastic optimal LQR control with integral quadratic constraints and indefinite control weightsIEEE Transactions on Automatic Control, 1999
- Nonlinear ProgrammingJournal of the Operational Research Society, 1997
- Application of vector performance optimization to a robust control loop design for a fighter aircraftInternational Journal of Control, 1983