An Iterative Scheme of Safe Reinforcement Learning for Nonlinear Systems via Barrier Certificate Generation.
Zhengfeng YangYidan ZhangWang LinXia ZengXiaochao TangZhenbing ZengZhiming LiuPublished in: CAV (1) (2021)
Keyphrases
- nonlinear systems
- reinforcement learning
- adaptive control
- stability analysis
- tracking control
- fuzzy model
- dead zone
- fuzzy control
- control law
- fuzzy systems
- learning rate
- adaptive neural
- controller design
- fuzzy controller
- lyapunov function
- inverted pendulum
- adaptive neural control
- chaotic systems
- optimal control
- decision making
- tracking error
- reinforcement learning algorithms
- control problems
- function approximation
- control strategy
- input output
- state space
- data mining