A Fast Approach to Satellite Range Rescheduling Using Deep Reinforcement Learning.
Jun LiangJian-Ping LiuQing SunYue-he ZhuYi-Chuan ZhangJian-Guo SongBo-Yong HePublished in: IEEE Trans. Aerosp. Electron. Syst. (2023)
Keyphrases
- reinforcement learning
- function approximation
- wide range
- state space
- remote sensing
- learning process
- autonomous learning
- deep learning
- temporal difference
- optimal control
- optimal policy
- dynamic programming
- markov decision processes
- range data
- bayesian networks
- learning algorithm
- real world
- learning agent
- action space
- function approximators
- neural network