An inertia wheel pendulum control method based on actor-critic learning algorithm.
Huanlong LiuZhengjie WangBin JiangHongyu PengPublished in: TrustCom (2021)
Keyphrases
- control method
- actor critic
- learning algorithm
- reinforcement learning
- reinforcement learning algorithms
- adaptive control
- control strategy
- control algorithm
- optimal control
- temporal difference
- policy gradient
- rl algorithms
- approximate dynamic programming
- pid controller
- control system
- function approximation
- fuzzy controller
- state space
- neuro fuzzy
- machine learning algorithms
- fuzzy control
- supervised learning
- lyapunov function
- policy iteration
- model free
- gradient method
- inverted pendulum
- machine learning
- learning rate
- learning tasks
- markov decision processes
- back propagation
- artificial neural networks
- feedback control
- control scheme
- manufacturing systems
- adaptive fuzzy
- multi agent