Finite-horizon optimal control for continuous-time uncertain nonlinear systems using reinforcement learning.
Jingang ZhaoMinggang GanPublished in: Int. J. Syst. Sci. (2020)
Keyphrases
- optimal control
- nonlinear systems
- finite horizon
- infinite horizon
- control law
- reinforcement learning
- optimal policy
- adaptive control
- average cost
- markov decision processes
- control problems
- markov decision process
- lyapunov function
- dynamic programming
- optimal control problems
- control strategy
- linear matrix inequality
- state space
- single product
- production planning
- feedback control
- fuzzy control
- fuzzy controller
- brownian motion
- actor critic
- learning rate
- rl algorithms
- fuzzy systems
- decision making
- hamilton jacobi bellman
- model free
- evolutionary algorithm
- temporal difference
- neural network
- sliding mode
- learning algorithm
- machine learning
- policy iteration
- multistage
- tracking error
- supply chain
- lyapunov stability
- fuzzy model
- linear programming