Shiftable Dynamic Policy Programming for Efficient and Robust Reinforcement Learning Control.
Zhiwei ShangHuiyun LiYunduan CuiPublished in: ROBIO (2021)
Keyphrases
- reinforcement learning
- control policy
- optimal policy
- control problems
- markov decision process
- dynamic environments
- computationally efficient
- action selection
- optimal control
- control strategy
- programming language
- control system
- learning process
- control policies
- robotic systems
- machine learning
- policy search
- control method
- highly efficient
- adaptive control