# Learning to Sail Dynamic Networks: The MARLIN Reinforcement Learning Framework for Congestion Control in Tactical Environments

arXiv: https://arxiv.org/abs/2306.15591 · HTML: https://mlsanity.com/paper/2306.15591/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 13 references that are in the map.
- First posted on arXiv 27 Jun 2023.

## Builds on (most cited first, 3 of 3)

- [MVFST-RL: An Asynchronous RL Framework for Congestion Control with Delayed Actions](https://mlsanity.com/paper/1910.04054/) (2019)
- [MeDICINE: Rapid Prototyping of Production-Ready Network Services in Multi-PoP Environments](https://mlsanity.com/paper/1606.05995/) (2016)
- [MARLIN: Soft Actor-Critic based Reinforcement Learning for Congestion Control in Real Networks](https://mlsanity.com/paper/2302.01301/) (2023)

## Built on by (most cited first, 2 of 2)

- [Collaborative Information Dissemination with Graph-based Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2308.16198/) (2023)
- [Distributed Autonomous Swarm Formation for Dynamic Network Bridging](https://mlsanity.com/paper/2404.01557/) (2024)

## Abstract (arXiv)

Conventional Congestion Control (CC) algorithms,such as TCP Cubic, struggle in tactical environments as they misinterpret packet loss and fluctuating network performance as congestion symptoms. Recent efforts, including our own MARLIN, have explored the use of Reinforcement Learning (RL) for CC, but they often fall short of generalization, particularly in competitive, unstable, and unforeseen scenarios. To address these challenges, this paper proposes an RL framework that leverages an accurate and parallelizable emulation environment to reenact the conditions of a tactical network. We also introduce refined RL formulation and performance evaluation methods tailored for agents operating in such intricate scenarios. We evaluate our RL learning framework by training a MARLIN agent in conditions replicating a bottleneck link transition between a Satellite Communication (SATCOM) and an UHF Wide Band (UHF) radio link. Finally, we compared its performance in file transfer tasks against Transmission Control Protocol (TCP) Cubic and the default strategy implemented in the Mockets tactical communication middleware. The results demonstrate that the MARLIN RL agent outperforms both TCP and Mockets under different perspectives and highlight the effectiveness of specialized RL solutions in optimizing CC for tactical network environments.