RBWE applies offline RL with Q-ensembles and Gaussian mixture policies to bandwidth estimation, cutting overestimation errors by 18% and raising the 10th percentile QoE by 18.6% over GCC.
ACM MMSys 2024 Bandwidth Estima- tion in Real Time Communications Challenge,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Robust Bandwidth Estimation for Real-Time Communication with Offline Reinforcement Learning
RBWE applies offline RL with Q-ensembles and Gaussian mixture policies to bandwidth estimation, cutting overestimation errors by 18% and raising the 10th percentile QoE by 18.6% over GCC.