Discrete-Time Nonlinear Optimal Control Using Multi-Step Reinforcement Learning.
Ningbo AnQishao WangXiaochuan ZhaoQingyun WangPublished in: IEEE Trans. Circuits Syst. II Express Briefs (2024)
Keyphrases
- optimal control
- multi step
- linear quadratic
- reinforcement learning
- optimal control problems
- class of nonlinear systems
- control problems
- dynamic programming
- lyapunov function
- feedback control
- infinite horizon
- actor critic
- continuous stirred tank reactor
- control strategy
- semi supervised
- knn
- control law
- function approximation
- k nearest neighbor
- state space
- learning algorithm
- temporal difference
- neural network
- rl algorithms
- markov chain
- feature vectors
- finite state
- reinforcement learning algorithms
- markov decision processes
- machine learning