Causal Policy Gradient for End-to-End Communication Systems.
Shounak ShirodkarSerene BanerjeePublished in: COMSNETS (2024)
Keyphrases
- end to end
- communication systems
- policy gradient
- reinforcement learning
- information processing systems
- computer systems
- function approximation
- gradient method
- blind equalization
- optimal control
- reinforcement learning algorithms
- wireless channels
- approximation methods
- bayesian networks
- variance reduction
- congestion control
- average reward
- multipath
- ad hoc networks
- state action
- single agent
- real time