On the optimization landscape of dynamic output feedback linear quadratic control

J Duan, W Cao, Y Zheng, L Zhao - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The convergence of policy gradient algorithms hinges on the optimization landscape of the
underlying optimal control problem. Theoretical insights into these algorithms can often be …

On the Optimization Landscape of Dynamic Output Feedback Linear Quadratic Control

J Duan, W Cao, Y Zheng, L Zhao - arXiv e-prints, 2022 - ui.adsabs.harvard.edu
The convergence of policy gradient algorithms hinges on the optimization landscape of the
underlying optimal control problem. Theoretical insights into these algorithms can often be …

On the Optimization Landscape of Dynamic Output Feedback Linear Quadratic Control

J Duan, W Cao, Y Zheng, L Zhao - arXiv preprint arXiv:2201.09598, 2022 - arxiv.org
The convergence of policy gradient algorithms hinges on the optimization landscape of the
underlying optimal control problem. Theoretical insights into these algorithms can often be …

[PDF][PDF] On the Optimization Landscape of Dynamic Output Feedback Linear Quadratic Control

J Duan, W Cao, Y Zheng, L Zhao - 2023 - researchgate.net
The convergence of policy gradient algorithms hinges on the optimization landscape of the
underlying optimal control problem. Theoretical insights into these algorithms can often be …

[PDF][PDF] On the Optimization Landscape of Dynamic Output Feedback Linear Quadratic Control

J Duan, W Cao, Y Zheng, L Zhao - researchgate.net
The optimization landscape of optimal control problems plays an important role in the
convergence of many policy gradient methods. Unlike state-feedback Linear Quadratic …

[引用][C] On the Optimization Landscape of Dynamic Output Feedback Linear Quadratic Control

J Duan, W Cao, Y Zheng, L Zhao - IEEE Transactions on Automatic Control, 2023 - IEEE