Model-free finite-horizon optimal tracking control of discrete-time linear systems.
Wei WangXiangpeng XieChangyang FengPublished in: Appl. Math. Comput. (2022)
Keyphrases
- finite horizon
- linear systems
- model free
- tracking control
- reinforcement learning
- optimal policy
- markov decision processes
- infinite horizon
- sufficient conditions
- multistage
- nonlinear systems
- average cost
- markov decision process
- function approximation
- finite state
- dynamical systems
- dynamic programming
- optimal solution
- optimal control
- markov chain
- long run
- control law
- adaptive neural
- machine learning
- learning algorithm