DDPG-E2E: A Novel Policy Gradient Approach for End-to-End Communication Systems.
Bolun ZhangNguyen Van HuynhDinh Thai HoangDiep N. NguyenQuoc-Viet PhamPublished in: CoRR (2024)
Keyphrases
- end to end
- communication systems
- policy gradient
- information processing systems
- computer systems
- gradient method
- function approximation
- reinforcement learning
- blind equalization
- optimal control
- approximation methods
- reinforcement learning algorithms
- wireless ad hoc networks
- multipath
- data processing
- variance reduction
- reinforcement learning methods
- state action
- partially observable markov decision processes
- congestion control
- wireless channels
- single agent
- ad hoc networks
- average reward
- multi agent