Reinforcement learning-based composite suboptimal control for Markov jump singularly perturbed systems with unknown dynamics
DOI10.1002/mma.10143MaRDI QIDQ6619376
Lei Su, Guolong Jia, Hao Shen, Wenqian Li, Yun Wang
Publication date: 15 October 2024
Published in: Mathematical Methods in the Applied Sciences (Search for Journal in Brave)
reinforcement learningcomposite controlMarkov jump singularly perturbed systemsfast and slow decomposition
Continuous-time Markov processes on general state spaces (60J25) Feedback control (93B52) Time-scale analysis and singular perturbations in control/observation systems (93C70) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Parallel algorithms in computer science (68W10)
This page was built for publication: Reinforcement learning-based composite suboptimal control for Markov jump singularly perturbed systems with unknown dynamics
