On-the-Fly Control of Unknown Nonlinear Systems With Sublinear Regret

DOI10.1109/TAC.2022.3186425MaRDI QIDQ6056029zbMATH OpenFDO

Authors A. P. Vinod, Arie Israel, Ufuk Topcu

Publication date 29 September 2023

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/TAC.2022.3186425

zbMATH Keywords

autonomous systemsestimationlearningoptimal controluncertain systems

Mathematics Subject Classification ID

Systems theory; control (93-XX)

Recommendations

• Controlling unknown linear dynamics with bounded multiplicative regret
• Online adaptive optimal control for continuous-time nonlinear systems with completely unknown dynamics
• Optimal online control of dynamical systems under uncertainty
• scientific article; zbMATH DE number 7266288
• Suboptimal reduced control of unknown nonlinear singularly perturbed systems via reinforcement learning
• Optimal on-line control under imperfect information
• Suboptimal learning control for nonlinear systems with both parametric and nonparametric uncertainties
• Reinforcement-learning-based online learning control for discrete-time unknown nonaffine nonlinear systems
• Online identifier-actor-critic algorithm for optimal control of nonlinear systems
• Discrete-time online learning control for a class of unknown nonaffine nonlinear systems using reinforcement learning

Cited in

(2)

• Logarithmic regret in online linear quadratic control using Riccati updates
• On-the-fly control of unknown nonlinear systems with sublinear regret

This page was built for publication: On-the-Fly Control of Unknown Nonlinear Systems With Sublinear Regret

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6056029)