Power Allocation for Full-Duplex Communication Systems Based on Deep Deterministic Policy Gradient.
Jin QuCongliang ZhuShengli LiuGuanding YuRui YinPublished in: GLOBECOM (Workshops) (2020)
Keyphrases
- communication systems
- policy gradient
- power allocation
- multiple input multiple output
- resource allocation
- mimo systems
- wireless channels
- computer systems
- optimal control
- reinforcement learning
- gradient method
- function approximation
- multiple access
- video transmission
- average reward
- channel estimation
- transmission scheme
- orthogonal frequency division multiplexing
- cognitive radio