Model-free multiobjective approximate dynamic programming for discrete-time nonlinear systems with general performance index functions.
Qinglai WeiHuaguang ZhangJing DaiPublished in: Neurocomputing (2009)
Keyphrases
- nonlinear systems
- model free
- approximate dynamic programming
- reinforcement learning
- multi objective
- policy iteration
- adaptive control
- dead zone
- fuzzy model
- fuzzy control
- reinforcement learning algorithms
- fuzzy controller
- fuzzy systems
- optimization algorithm
- evolutionary algorithm
- temporal difference
- learning rate
- machine learning
- control law
- input output
- state space
- dynamic programming
- genetic algorithm