Reinforcement learning for bandwidth estimation and congestion control in real-time communications.
Joyce FangMartin EllisBin LiSiyao LiuYasaman HosseinkashiMichael RevowAlbert SadovnikovZiyuan LiuPeng ChengSachin AshokDavid ZhaoRoss CutlerYan LuJohannes GehrkePublished in: CoRR (2019)
Keyphrases
- congestion control
- real time
- end to end
- reinforcement learning
- quality of service
- transmission rate
- network bandwidth
- packet loss
- window size
- packet losses
- congestion avoidance
- wireless link
- transport protocol
- network congestion
- rate control
- ad hoc networks
- network conditions
- rate adaptation
- bandwidth allocation
- link utilization
- multicast tree
- differentiated services
- high speed
- network resources
- sliding window