Deep Reinforcement Learning for Delay-Oriented IoT Task Scheduling in SAGIN.
Conghao ZhouWen WuHongli HePeng YangFeng LyuNan ChengXuemin ShenPublished in: IEEE Trans. Wirel. Commun. (2021)
Keyphrases
- reinforcement learning
- function approximation
- management system
- resource management
- machine learning
- model free
- scheduling algorithm
- markov decision processes
- cloud computing
- learning algorithm
- temporal difference
- optimal policy
- transfer learning
- state space
- learning process
- optimal control
- computing systems
- reinforcement learning algorithms
- dynamic programming
- grid computing
- data sets
- cloud computing environment