Adaptive Dynamic Programming for Finite-Horizon Optimal Control of Discrete-Time Nonlinear Systems With varepsilon-Error Bound.
Fei-Yue WangN. JinD. LiuQ. WeiPublished in: IEEE Trans. Neural Networks (2011)
Keyphrases
- optimal control
- infinite horizon
- nonlinear systems
- error bounds
- finite horizon
- control law
- dynamic programming
- adaptive control
- optimal control problems
- lyapunov function
- optimal policy
- adaptive neural
- average cost
- control problems
- tracking error
- theoretical analysis
- markov decision processes
- multistage
- control strategy
- production planning
- feedback control
- dead zone
- reinforcement learning
- single product
- hamilton jacobi bellman
- fuzzy control
- state space
- worst case
- fuzzy model
- brownian motion
- learning rate
- markov chain
- markov decision process
- linear programming
- stochastic control
- lyapunov stability
- dynamic environments
- control method
- input output
- mathematical model
- closed loop
- control algorithm
- special case
- learning algorithm