Continuous-time reinforcement learning for robust control under worst-case uncertainty

DOI10.1080/00207721.2020.1839142zbMath1483.93111OpenAlexW3097267952MaRDI QIDQ5028006

Adolfo Perrusquía, Wen Yu

Publication date: 8 February 2022

Published in: International Journal of Systems Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/00207721.2020.1839142

zbMATH Keywords

robust controlunknown nonlinear systemsworst case uncertaintycontinuous-time reinforcement learning

Mathematics Subject Classification ID

Sensitivity (robustness) (93B35) Nonlinear systems in control theory (93C10) Control/observation systems with incomplete information (93C41)

Related Items (2)

Stable robot manipulator parameter identification: a closed-loop input error approach ⋮ Solution of the linear quadratic regulator problem of black box linear systems using reinforcement learning

Cites Work

• Unnamed Item
• Q-learning for continuous-time linear systems: A model-free infinite horizon optimal control approach
• Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem
• Robust reinforcement learning control with static and dynamic stability
• Continuous-time path planning for multi-agents with fuzzy reinforcement learning
• Robust control under worst‐case uncertainty for unknown nonlinear systems using modified reinforcement learning
• Designing of robust adaptive passivity-based controller based on reinforcement learning for nonlinear port-Hamiltonian model with disturbance
• Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers

This page was built for publication: Continuous-time reinforcement learning for robust control under worst-case uncertainty