Robust Bandwidth Estimation for Real-Time Communication with Offline Reinforcement Learning

TL;DR

This paper introduces RBWE, an offline RL-based framework for bandwidth estimation in real-time communication, addressing challenges like OOD actions and deployment stability, and demonstrating significant improvements in QoE and error reduction.

Contribution

The paper presents a novel offline RL approach with Q-ensembles and Gaussian policies for robust bandwidth estimation, including a fallback mechanism for deployment stability.

Findings

Reduces overestimation errors by 18%

Improves 10th percentile QoE by 18.6%

Enhances robustness in real-world RTC applications

Abstract

Accurate bandwidth estimation (BWE) is critical for real-time communication (RTC) systems. Traditional heuristic approaches offer limited adaptability under dynamic networks, while online reinforcement learning (RL) suffers from high exploration costs and potential service disruptions. Offline RL, which leverages high-quality data collected from real-world environments, offers a promising alternative. However, challenges such as out-of-distribution (OOD) actions, policy extraction from behaviorally diverse datasets, and reliable deployment in production systems remain unsolved. We propose RBWE, a robust bandwidth estimation framework based on offline RL that integrates Q-ensemble (an ensemble of Q-functions) with a Gaussian mixture policy to mitigate OOD risks and enhance policy learning. A fallback mechanism ensures deployment stability by switching to heuristic methods under high uncertainty. Experimental results show that RBWE reduces overestimation errors by 18% and improves the 10th percentile Quality of Experience (QoE) by 18.6%, demonstrating its practical effectiveness in real-world RTC applications. The implementation is publicly available at https://github.com/jiu2021/RBWE_offline.