Reinforcement Learning Policy with Proportional-Integral Control.
Ye HuangChaochen GuKaijie WuXinping GuanPublished in: ICONIP (3) (2018)
Keyphrases
- reinforcement learning
- control policy
- action selection
- optimal policy
- control policies
- optimal control
- function approximators
- control strategy
- function approximation
- policy search
- reinforcement learning algorithms
- state space
- control system
- control strategies
- reward function
- action space
- policy gradient
- artificial intelligence
- control method
- dynamic programming
- machine learning
- adaptive control
- model free