Proceedings

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

Thanh Dat Le, Lyuzhou Ye, Yan Huang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 152-160.

https://doi.org/10.24963/ijcai.2025/18

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

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.

Thanh Dat Le, Lyuzhou Ye, and Yan Huang. 2025. RoLocMe: A Robust Multi-agent Source Localization System with Learning-based Map Estimation. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 152–160. https://doi.org/10.24963/ijcai.2025/18
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards