Q-learning based tracking control with novel finite-horizon performance index.
Wei WangKe WangZixin HuangChaoxu MuHaoxian ShiPublished in: Inf. Sci. (2024)
Keyphrases
- finite horizon
- tracking control
- optimal policy
- nonlinear systems
- markov decision processes
- infinite horizon
- state space
- reinforcement learning
- multistage
- control law
- long run
- dynamic programming
- markov decision process
- finite state
- learning rate
- average cost
- adaptive neural
- multi agent
- fuzzy model
- optimal control
- control system
- non stationary
- sufficient conditions
- neural network
- computational intelligence
- initial state
- control algorithm
- adaptive control
- machine learning
- artificial neural networks
- robust tracking
- dynamical systems
- closed loop
- fuzzy clustering
- fuzzy control
- multi robot
- fuzzy controller