ACM MMSys 2024 Bandwidth Estimation in Real Time Communications Challenge

TL;DR

This paper presents a challenge to improve real-time communication bandwidth estimation by using offline reinforcement learning with real-world data to better align network models with user-perceived quality.

Contribution

It introduces a new challenge framework that leverages real-world data and offline RL to enhance bandwidth estimation models for RTC, addressing the sim-to-real gap.

Findings

Offline RL models using real-world data perform comparably to top policies.

Objective quality scores as rewards improve model relevance to user experience.

Evaluation on diverse network conditions demonstrates robustness of proposed models.

Abstract

The quality of experience (QoE) delivered by video conferencing systems to end users depends in part on correctly estimating the capacity of the bottleneck link between the sender and the receiver over time. Bandwidth estimation for real-time communications (RTC) remains a significant challenge, primarily due to the continuously evolving heterogeneous network architectures and technologies. From the first bandwidth estimation challenge which was hosted at ACM MMSys 2021, we learned that bandwidth estimation models trained with reinforcement learning (RL) in simulations to maximize network-based reward functions may not be optimal in reality due to the sim-to-real gap and the difficulty of aligning network-based rewards with user-perceived QoE. This grand challenge aims to advance bandwidth estimation model design by aligning reward maximization with user-perceived QoE optimization using offline RL and a real-world dataset with objective rewards which have high correlations with subjective audio/video quality in Microsoft Teams. All models submitted to the grand challenge underwent initial evaluation on our emulation platform. For a comprehensive evaluation under diverse network conditions with temporal fluctuations, top models were further evaluated on our geographically distributed testbed by using each model to conduct 600 calls within a 12-day period. The winning model is shown to deliver comparable performance to the top behavior policy in the released dataset. By leveraging real-world data and integrating objective audio/video quality scores as rewards, offline RL can therefore facilitate the development of competitive bandwidth estimators for RTC.