Deep Deterministic Policy Gradient for End-to-End Communication Systems without Prior Channel Knowledge.
Bolun ZhangNguyen Van HuynhPublished in: CoRR (2023)
Keyphrases
- end to end
- communication systems
- multiple access
- channel estimation
- wireless channels
- blind equalization
- multipath
- information processing systems
- rate allocation
- ad hoc networks
- computer systems
- policy gradient
- congestion control
- function approximation
- machine learning
- computer simulation
- data processing
- multi agent
- reinforcement learning