Escaping high-order saddles in policy optimization for Linear Quadratic Gaussian (LQG) control

Y Zheng, Y Sun, M Fazel, N Li - 2022 IEEE 61st Conference on …, 2022 - ieeexplore.ieee.org
First-order policy optimization has been widely used in reinforcement learning. It guarantees
to find the optimal policy for the state-feedback linear quadratic regulator (LQR). However …
被引用次数：16 相关文章

Escaping High-order Saddles in Policy Optimization for Linear Quadratic Gaussian (LQG) Control

Y Zheng, Y Sun, M Fazel, N Li - arXiv preprint arXiv:2204.00912, 2022 - arxiv.org
First order policy optimization has been widely used in reinforcement learning. It guarantees
to find the optimal policy for the state-feedback linear quadratic regulator (LQR). However …
[PDF] researchgate.net

[PDF][PDF] Escaping High-order Saddles in Policy Optimization for Linear Quadratic Gaussian (LQG) Control

Y Zheng, Y Sun, M Fazel, N Li - arXiv preprint arXiv:2204.00912, 2022 - researchgate.net
First order policy optimization has been widely used in reinforcement learning. It guarantees
to find the optimal policy for the state-feedback linear quadratic regulator (LQR). However …
[PDF] github.io

[PDF][PDF] Escaping High-order Saddles in Policy Optimization for Linear Quadratic Gaussian (LQG) Control

Y Zheng - 2022 - zhengy09.github.io
Escaping High-order Saddles in Policy Optimization for Linear Quadratic Gaussian (LQG)
Control Page 1 Escaping High-order Saddles in Policy Optimization for Linear Quadratic …

Escaping High-order Saddles in Policy Optimization for Linear Quadratic Gaussian (LQG) Control

Y Zheng, Y Sun, M Fazel, N Li - arXiv e-prints, 2022 - ui.adsabs.harvard.edu
First order policy optimization has been widely used in reinforcement learning. It guarantees
to find the optimal policy for the state-feedback linear quadratic regulator (LQR). However …
[PDF] nsf.gov

[PDF][PDF] Escaping High-order Saddles in Policy Optimization for Linear Quadratic Gaussian (LQG) Control

Y Zheng, Y Sun, M Fazel, N Li - IEEE 61st Conference on Decision and …, 2022 - par.nsf.gov
First-order policy optimization has been widely used in reinforcement learning. It guarantees
to find the optimal policy for the state-feedback linear quadratic regulator (LQR). However …
[PDF] github.io

[PDF][PDF] Escaping High-order Saddles in Policy Optimization for Linear Quadratic Gaussian (LQG) Control

Y Zheng, Y Sun, M Fazel, N Li - zhengy09.github.io
First order policy optimization has been widely used in reinforcement learning. It guarantees
to find the optimal policy for the state-feedback linear quadratic regulator (LQR). However …