Robust policy iteration of uncertain interconnected systems with imperfect data

O Qasem, W Gao - IEEE Transactions on Automation Science …, 2023 - ieeexplore.ieee.org
This paper investigates the robust optimal control problem of a class of continuous-time,
partially linear, interconnected systems. In addition to the dynamic uncertainties resulted …

Robust control design for linear systems via multiplicative noise

BJ Gravell, PM Esfahani, TH Summers - IFAC-PapersOnLine, 2020 - Elsevier
Robust stability and stochastic stability have separately seen intense study in control theory
for many decades. In this work we establish relations between these properties for discrete …

Adaptive exploration policy for exploration–exploitation tradeoff in continuous action control optimization

M Li, T Huang, W Zhu - International Journal of Machine Learning and …, 2021 - Springer
The optimization of continuous action control is an important research field. It aims to find
optimal decisions by the experience of making decisions in a continuous action control task …

Safe learning LQR of linear dynamics with multiplicative noise

P Coppens, P Patrinos - arXiv preprint arXiv:2207.06062, 2022 - arxiv.org
Control of linear dynamics with multiplicative noise naturally introduces robustness against
dynamical uncertainty. Moreover, many physical systems are subject to multiplicative …

Provably stable learning control of linear dynamics with multiplicative noise

P Coppens, P Patrinos - IEEE Transactions on Automatic …, 2023 - ieeexplore.ieee.org
Control of linear dynamics with multiplicative noise naturally introduces robustness against
dynamical uncertainty. Moreover, many physical systems are subject to multiplicative …

Stochastic stability via robustness of linear systems

B Gravell, T Summers - … 60th IEEE Conference on Decision and …, 2021 - ieeexplore.ieee.org
Robust stability and stochastic stability have separately seen intense study in control theory
since its inception. In this work we establish relations between these properties for discrete …

Policy iteration for multiplicative noise output feedback control

B Gravell, M Gargiani, J Lygeros… - 2022 IEEE 61st …, 2022 - ieeexplore.ieee.org
We propose a policy iteration algorithm for solving the multiplicative noise linear quadratic
output feedback design problem. The algorithm solves a set of coupled Riccati equations for …

Exploration Decay Policy (EDP) to Enhanced Exploration-Exploitation Trade-Off in DDPG for Continuous Action Control Optimization

EH Sumiea, SJ AbdulKadir, H Alhussian… - 2023 IEEE 21st …, 2023 - ieeexplore.ieee.org
The optimization of continuous action control tasks is a crucial step in deep reinforcement
learning (DRL) applications. The goal is to identify optimal actions through the accumulation …

Conformal Robust Control of Linear Systems

Y Patel, S Rayan, A Tewari - arXiv preprint arXiv:2405.16250, 2024 - arxiv.org
End-to-end engineering design pipelines, in which designs are evaluated using
concurrently defined optimal controllers, are becoming increasingly common in practice. To …

Robust Data-Driven Output Feedback Control via Bootstrapped Multiplicative Noise

B Gravell, I Shames, T Summers - Learning for Dynamics …, 2022 - proceedings.mlr.press
We propose a robust data-driven output feedback control algorithm that explicitly
incorporates inherent finite-sample model estimate uncertainties into the control design. The …