Deep Reinforcement Learning for Optimization of RAN Slicing Relying on Control- and User-Plane Separation.
Haiyan TuLiqiang ZhaoYaoyuan ZhangGan ZhengChen FengShenghui SongKai LiangPublished in: IEEE Internet Things J. (2024)
Keyphrases
- reinforcement learning
- control problems
- optimization algorithm
- user interface
- global optimization
- user preferences
- user interaction
- dynamic programming
- home environment
- information retrieval
- action selection
- model free
- user profiles
- optimization problems
- end users
- control system
- multi agent
- three dimensional
- learning algorithm
- user behavior
- optimization method
- recommender systems
- optimization process
- control strategies
- robot control
- genetic algorithm