---
title: "RoLocMe: A Robust Multi-agent Source Localization System with Learning-based Map Estimation"
authors:
  - "Thanh Dat Le"
  - "Lyuzhou Ye"
  - "Yan Huang"
doi: "10.24963/ijcai.2025/18"
url: "https://ijcai.org/proceedings/2025/18"
pdf: "https://ijcai.org/proceedings/2025/0018.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "152-160"
track: "Main Track"
keywords:
  - "Agent-based and Multi-agent Systems: MAS: Applications"
  - "Machine Learning: ML: Multiagent Reinforcement Learning"
  - "Agent-based and Multi-agent Systems: MAS: Multi-agent planning"
  - "Planning and Scheduling: PS: Distributed and multi-agent planning"
---

# RoLocMe: A Robust Multi-agent Source Localization System with Learning-based Map Estimation

Thanh Dat Le, Lyuzhou Ye, Yan Huang

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 152-160. DOI: [10.24963/ijcai.2025/18](https://doi.org/10.24963/ijcai.2025/18)

## Abstract

This paper addresses the source localization problem by introducing RoLocMe, a multi-agent reinforcement learning system that integrates SkipNet - a skip-connection-based RSS estimation model - with parallel Q-learning. SkipNet predicts RSS propagation of the entire search region, enabling agents to explore efficiently. The agents leverage dueling DQN, value decomposition, and λ-returns to learn cooperative policies. RoLocMe converges faster and achieves at least 20% higher success rates than existing methods in dense and sparse reward settings. A drop-one ablation study confirms each component’s importance and RoLocMe’s effectiveness for larger teams.