1 citations · 2 across the 11 of their papers we have counts for
11 papers
Direct Data-Driven Linear Quadratic Tracking via Policy Optimization
Shubo Kang, Keyou You
Direct data-driven optimal control provides an elegant end-to-end paradigm, yet its real-time applicability is often hindered by the growing dimensionality of online decision varia…
Adaptive Polyak Stepsize with Level-value Adjustment for Distributed Optimization
Chen Ouyang, Yongyang Xiong, Jinming Xu +2
Stepsize selection remains a critical challenge in the practical implementation of distributed optimization. Existing distributed algorithms often rely on restrictive prior knowled…
Loopless Proximal Riemannian Gradient EXTRA for Distributed Optimization on Compact Manifolds
Yongyang Xiong, Chen Ouyang, Keyou You +2
Distributed optimization has gained substantial interest in recent years due to its wide applications in machine learning. However, most of existing algorithms are designed for Euc…
Heterogeneous Stochastic Momentum ADMM for Distributed Nonconvex Composite Optimization
Yangming Zhang, Yongyang Xiong, Jinming Xu +2
This paper investigates the distributed stochastic nonconvex and nonsmooth composite optimization problem. Existing stochastic typically rely on uniform step size strictly bounded…
Compressed Proximal Federated Learning for Non-Convex Composite Optimization on Heterogeneous Data
Pu Qiu, Chen Ouyang, Yongyang Xiong +3
Federated Composite Optimization (FCO) has emerged as a promising framework for training models with structural constraints (e.g., sparsity) in distributed edge networks. However,…
Direct Adaptive Control of Grid-Connected Power Converters via Output-Feedback Data-Enabled Policy Optimization
Feiran Zhao, Ruohan Leng, Linbin Huang +3
Power electronic converters are becoming the main components of modern power systems due to the increasing integration of renewable energy sources. However, power converters may be…
Linear Convergence of Data-Enabled Policy Optimization for Linear Quadratic Tracking
Shubo Kang, Feiran Zhao, Keyou You
Data-enabled policy optimization (DeePO) is a newly proposed method to attack the open problem of direct adaptive LQR. In this work, we extend the DeePO framework to the linear qua…
Asynchronous Parallel Policy Gradient Methods for the Linear Quadratic Regulator
Xingyu Sha, Feiran Zhao, Keyou You
Learning policies in an asynchronous parallel way is essential to the numerous successes of RL for solving large-scale problems. However, their convergence performance is still not…
Policy Gradient Methods for the Cost-Constrained LQR: Strong Duality and Global Convergence
Feiran Zhao, Keyou You
In safety-critical applications, reinforcement learning (RL) needs to consider safety constraints. However, theoretical understandings of constrained RL for continuous control are…
Harnessing Data for Accelerating Model Predictive Control by Constraint Removal
Zhinan Hou, Feiran Zhao, Keyou You
Model predictive control (MPC) solves a receding-horizon optimization problem in real-time, which can be computationally demanding when there are thousands of constraints. To accel…
Data-Enabled Policy Optimization for Direct Adaptive Learning of the LQR
Feiran Zhao, Florian Dörfler, Alessandro Chiuso +1
Direct data-driven design methods for the linear quadratic regulator (LQR) mainly use offline or episodic data batches, and their online adaptation has been acknowledged as an open…