4 papers · 1 filter
Adaptive Linear Quadratic Control of Unknown Linear Time-Varying Systems via Policy Gradient Methods
Feiran Zhao, Florian Dörfler
Unknown linear time-varying (LTV) systems require the control policy to adapt from online closed-loop data as dynamics evolve. Existing methods usually update the policy by solving…
A Bayesian Perspective on the Data-Driven LQR
Thierry Schwaller, Feiran Zhao, Florian Dörfler
The data-driven linear quadratic regulator (ddLQR) is a widely studied control method for unknown dynamical systems with disturbance. Existing approaches, both indirect, i.e., thos…
Adaptive Control of Unknown Linear Switched Systems via Policy Gradient Methods
Felix Laurent, Feiran Zhao, Jaap Eising +1
We consider the policy gradient adaptive control (PGAC) framework, which adaptively updates a control policy in real time, by performing data-based gradient descent steps on the li…
Policy Gradient Adaptive Control for the LQR: Indirect and Direct Approaches
Feiran Zhao, Alessandro Chiuso, Florian Dörfler
Motivated by recent advances of reinforcement learning and direct data-driven control, we propose policy gradient adaptive control (PGAC) for the linear quadratic regulator (LQR),…