Optimal Output Regulation for Model-Free Quanser Helicopter With Multistep Q-Learning.
Biao LuoHuai-Ning WuTingwen HuangPublished in: IEEE Trans. Ind. Electron. (2018)
Keyphrases
- model free
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- average reward
- policy iteration
- temporal difference
- dynamic programming
- hierarchical reinforcement learning
- policy evaluation
- impedance control
- rl algorithms
- optimal control
- mathematical model
- closed loop
- dynamical systems
- markov chain
- active learning
- pattern recognition
- training data
- machine learning