Reinforcement learning for bandwidth estimation and congestion control in real-time communications

TL;DR

This paper explores the novel application of reinforcement learning to optimize bandwidth estimation and congestion control in real-time communications, aiming to improve user experience amidst network variability.

Contribution

It introduces the first reinforcement learning approach for real-time communication control, demonstrating initial proof-of-concept results in simulation and real Internet video calls.

Findings

RL agent can control sending rate in RTC systems

Challenges include designing realistic reward functions

Bridging training and real-world network environments is complex

Abstract

Bandwidth estimation and congestion control for real-time communications (i.e., audio and video conferencing) remains a difficult problem, despite many years of research. Achieving high quality of experience (QoE) for end users requires continual updates due to changing network architectures and technologies. In this paper, we apply reinforcement learning for the first time to the problem of real-time communications (RTC), where we seek to optimize user-perceived quality. We present initial proof-of-concept results, where we learn an agent to control sending rate in an RTC system, evaluating using both network simulation and real Internet video calls. We discuss the challenges we observed, particularly in designing realistic reward functions that reflect QoE, and in bridging the gap between the training environment and real-world networks.