Internet Congestion Control via Deep Reinforcement Learning

TL;DR

This paper explores the application of deep reinforcement learning to Internet congestion control, demonstrating its potential to outperform existing methods while discussing challenges like fairness and safety.

Contribution

It introduces a novel RL-based approach for congestion control, along with a test suite for reproducibility and further research.

Findings

RL policies outperform state-of-the-art congestion control methods

Identifies key challenges: fairness, safety, generalization

Provides a test suite for RL congestion control research

Abstract

We present and investigate a novel and timely application domain for deep reinforcement learning (RL): Internet congestion control. Congestion control is the core networking task of modulating traffic sources' data-transmission rates to efficiently utilize network capacity, and is the subject of extensive attention in light of the advent of Internet services such as live video, virtual reality, Internet-of-Things, and more. We show that casting congestion control as RL enables training deep network policies that capture intricate patterns in data traffic and network conditions, and leverage this to outperform the state-of-the-art. We also highlight significant challenges facing real-world adoption of RL-based congestion control, including fairness, safety, and generalization, which are not trivial to address within conventional RL formalism. To facilitate further research and reproducibility of our results, we present a test suite for RL-guided congestion control based on the OpenAI Gym interface.