Scaling Multi Agent Reinforcement Learning for Underwater Acoustic Tracking via Autonomous Vehicles

TL;DR

This paper presents a scalable framework combining iterative simulation distillation and a Transformer-based MARL architecture, enabling efficient training and deployment of autonomous underwater vehicle fleets for multi-target tracking with high accuracy.

Contribution

It introduces a novel iterative distillation method for high-fidelity simulation acceleration and a Transformer-based MARL model that is invariant to the number of agents and targets.

Findings

Achieves up to 30,000x speedup in simulation training.

Maintains tracking errors below 5 meters in complex scenarios.

Enables scalable, high-precision underwater tracking with autonomous vehicles.

Abstract

Autonomous vehicles (AV) offer a cost-effective solution for scientific missions such as underwater tracking. Recently, reinforcement learning (RL) has emerged as a powerful method for controlling AVs in complex marine environments. However, scaling these techniques to a fleet--essential for multi-target tracking or targets with rapid, unpredictable motion--presents significant computational challenges. Multi-Agent Reinforcement Learning (MARL) is notoriously sample-inefficient, and while high-fidelity simulators like Gazebo's LRAUV provide 100x faster-than-real-time single-robot simulations, they offer no significant speedup for multi-vehicle scenarios, making MARL training impractical. To address these limitations, we propose an iterative distillation method that transfers high-fidelity simulations into a simplified, GPU-accelerated environment while preserving high-level dynamics. This approach achieves up to a 30,000x speedup over Gazebo through parallelization, enabling efficient training via end-to-end GPU acceleration. Additionally, we introduce a novel Transformer-based architecture (TransfMAPPO) that learns multi-agent policies invariant to the number of agents and targets, significantly improving sample efficiency. Following large-scale curriculum learning conducted entirely on GPU, we perform extensive evaluations in Gazebo, demonstrating that our method maintains tracking errors below 5 meters over extended durations, even in the presence of multiple fast-moving targets. This work bridges the gap between large-scale MARL training and high-fidelity deployment, providing a scalable framework for autonomous fleet control in real-world sea missions.