DEAR: DRL Empowered Actor-Critic ScheduleR for Multipath QUIC Under 5G/B5G Hybrid Networks.

Pattiwar Shravan Kumar Paresh Saxena Özgü Alay

Published in: AINA (1) (2024)

Keyphrases

multipath
actor critic
end to end
multiple paths
routing algorithm
antenna array
reinforcement learning
multipath routing
bit error rate
gradient method
policy gradient
temporal difference
approximate dynamic programming
function approximation
optimal control
machine learning
real time
neuro fuzzy
frequency domain