5 papers · 1 filter
Convergence in On-line Learning of Static and Dynamic Systems
Torbjörn Wigren, Ruoqi Zhang, Per Mattsson
The paper derives analytical expressions for the asymptotic average updating direction of the adaptive moment generation (ADAM) algorithm when applied to recursive identification o…
Safe Output Feedback Improvement with Baselines
Ruoqi Zhang, Per Mattsson, Dave Zachariah
In data-driven control design, an important problem is to deal with uncertainty due to limited and noisy data. One way to do this is to use a min-max approach, which aims to minimi…
Aiding reinforcement learning for set point control
Ruoqi Zhang, Per Mattsson, Torbjörn Wigren
While reinforcement learning has made great improvements, state-of-the-art algorithms can still struggle with seemingly simple set-point feedback control problems. One reason for t…
Robust nonlinear set-point control with reinforcement learning
Ruoqi Zhang, Per Mattsson, Torbjörn Wigren
There has recently been an increased interest in reinforcement learning for nonlinear control problems. However standard reinforcement learning algorithms can often struggle even o…
Observer-Feedback-Feedforward Controller Structures in Reinforcement Learning
Ruoqi Zhang, Per Mattson, Torbjörn Wigren
The paper proposes the use of structured neural networks for reinforcement learning based nonlinear adaptive control. The focus is on partially observable systems, with separate ne…