Optimal control for continuous-time Markov jump singularly perturbed systems : A hybrid reinforcement learning scheme.
Yaling HuangWenqian LiYun WangHao ShenPublished in: J. Frankl. Inst. (2024)
Keyphrases
- optimal control
- learning scheme
- reinforcement learning
- control problems
- markov chain
- dynamic programming
- control strategy
- learning algorithm
- feedback control
- infinite horizon
- brownian motion
- optimal control problems
- markov processes
- risk sensitive
- rule learning
- control law
- average cost
- control scheme
- supply chain
- class of nonlinear systems