Deep Reinforcement Learning Powered IRS-Assisted Downlink NOMA.
Muhammad ShehabBekir Sait CiftlerTamer KhattabMohamed M. AbdallahDaniele TrincheroPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- resource allocation
- function approximation
- markov decision processes
- optimal policy
- reinforcement learning algorithms
- machine learning
- application layer
- temporal difference
- model free
- transfer learning
- supervised learning
- state space
- learning algorithm
- software implementation
- policy search
- belief nets
- robotic control
- action selection
- video sequences
- deep learning
- function approximators
- neural network
- temporal difference learning