Reinforcement Learning-Based Near Optimization for Continuous-Time Markov Jump Singularly Perturbed Systems.
Jing WangChuanjun PengJu H. ParkHao ShenKaibo ShiPublished in: IEEE Trans. Circuits Syst. II Express Briefs (2023)
Keyphrases
- markov chain
- reinforcement learning
- optimal control
- state space
- markov decision processes
- complex systems
- optimization problems
- distributed systems
- function approximation
- retrieval systems
- database
- real time
- multi objective
- expert systems
- building blocks
- web services
- search engine
- dynamical systems
- data mining
- optimization method
- learning tasks
- neural network