Deep Q‐learning: A robust control approach

DOI10.1002/rnc.6457zbMath1530.93087arXiv2201.08610OpenAlexW4307820093MaRDI QIDQ6136628

Morteza Haghir Chehreghani, Balázs Kulcsár, Balázs Varga

Publication date: 17 January 2024

Published in: International Journal of Robust and Nonlinear Control (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2201.08610

zbMATH Keywords

robust controldeep Q-learningneural tangent kernelcontrolled learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Sensitivity (robustness) (93B35) Feedback control (93B52) (H^infty)-control (93B36)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Beyond singular values and loop shapes
• Robust reinforcement learning control with static and dynamic stability
• H_∞ tracking control for linear discrete‐time systems via reinforcement learning
• Robust control under worst‐case uncertainty for unknown nonlinear systems using modified reinforcement learning
• Wide neural networks of any depth evolve as linear models under gradient descent ^*

This page was built for publication: Deep Q‐learning: A robust control approach