A dual-layer adaptive HARQ mechanism based on reinforcement learning for 5G Non-Terrestrial communications.
Zikai XuChuanyu LiangDanpu LiuZhilong ZhangPublished in: ICCIP (2023)
Keyphrases
- reinforcement learning
- multi layer
- machine learning
- function approximation
- state space
- adaptive control
- reinforcement learning algorithms
- learning capabilities
- evolutionary algorithm
- optimal policy
- communication networks
- temporal difference learning
- lidar data
- multi agent reinforcement learning
- protocol stack
- robotic control