Convergence Analysis of Value Iteration Adaptive Dynamic Programming for Continuous-Time Nonlinear Systems.
Geyang XiaoHuaguang ZhangPublished in: IEEE Trans. Cybern. (2024)
Keyphrases
- nonlinear systems
- convergence analysis
- dynamic programming
- adaptive control
- state space
- optimal control
- control law
- markov decision processes
- reinforcement learning
- global convergence
- fuzzy model
- infinite horizon
- optimal policy
- learning rate
- adaptive neural control
- control method
- fuzzy systems
- approximation methods
- optimality conditions
- dynamical systems
- convergence rate
- linear programming
- markov decision process
- policy iteration
- dynamic environments
- neural network
- input output
- membership functions
- computational intelligence
- evolutionary algorithm
- search algorithm