User Pairing for Delay-Limited NOMA-Based Satellite Networks with Deep Reinforcement Learning.
Qianfeng ZhangKang AnXiaojuan YanHongxia XiYuli WangPublished in: Sensors (2023)
Keyphrases
- reinforcement learning
- user interface
- social networks
- user experience
- machine learning
- reinforcement learning algorithms
- computer networks
- complex networks
- user profiles
- user interaction
- recommender systems
- multi agent
- learning algorithm
- end users
- relevance feedback
- dynamic programming
- network structure
- mobile devices
- function approximation
- optimal control
- neural network