activity
20192024
most citedData-driven Control of Unknown Linear Systems via Quantized Feedback

3 citations · 6 across the 7 of their papers we have counts for

collaborators
Showing math.OCShow all

6 papers · 1 filter

math.OC2024

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…

math.OC20241 cited

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…

math.OC20241 cited

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…

math.OC2023

Data-enabled Policy Optimization for the Linear Quadratic Regulator

Feiran Zhao, Florian Dörfler, Keyou You

Policy optimization (PO), an essential approach of reinforcement learning for a broad range of system classes, requires significantly more system data than indirect (identification…

math.OC20223 cited

Data-driven Control of Unknown Linear Systems via Quantized Feedback

Feiran Zhao, Xingchen Li, Keyou You

Control using quantized feedback is a fundamental approach to system synthesis with limited communication capacity. In this paper, we address the stabilization problem for unknown…

math.OC20212 cited

Infinite-horizon Risk-constrained Linear Quadratic Regulator with Average Cost

Feiran Zhao, Keyou You, Tamer Basar

The behaviour of a stochastic dynamical system may be largely influenced by those low-probability, yet extreme events. To address such occurrences, this paper proposes an infinite-…