Leveraging Deep Reinforcement Learning for Geolocation-based MIMO Transmission in FD-RAN.
Zongxi LiuKai YuTianqi ZhangJingbo LiuJiacheng ChenHaibo ZhouXuemin Sherman ShenPublished in: ICCC (2023)
Keyphrases
- reinforcement learning
- mimo ofdm
- fading channels
- multiple input multiple output
- transmission scheme
- mimo systems
- function approximation
- learning algorithm
- physical layer
- optimal control
- markov decision processes
- data transmission
- wireless systems
- reinforcement learning algorithms
- cdma systems
- optimal policy
- wireless channels
- temporal difference
- dynamic programming
- action space
- video sequences
- ofdm system
- action selection
- low complexity
- transfer learning
- state space