Goal-Oriented Multi-Agent Reinforcement Learning for Decentralized Agent Teams

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Du, Hung, Nguyen, Hy, Thudumu, Srikanth, Vasa, Rajesh, Mouzakis, Kon
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917081300074496
author Du, Hung
Nguyen, Hy
Thudumu, Srikanth
Vasa, Rajesh
Mouzakis, Kon
author_facet Du, Hung
Nguyen, Hy
Thudumu, Srikanth
Vasa, Rajesh
Mouzakis, Kon
contents Connected and autonomous vehicles across land, water, and air must often operate in dynamic, unpredictable environments with limited communication, no centralized control, and partial observability. These real-world constraints pose significant challenges for coordination, particularly when vehicles pursue individual objectives. To address this, we propose a decentralized Multi-Agent Reinforcement Learning (MARL) framework that enables vehicles, acting as agents, to communicate selectively based on local goals and observations. This goal-aware communication strategy allows agents to share only relevant information, enhancing collaboration while respecting visibility limitations. We validate our approach in complex multi-agent navigation tasks featuring obstacles and dynamic agent populations. Results show that our method significantly improves task success rates and reduces time-to-goal compared to non-cooperative baselines. Moreover, task performance remains stable as the number of agents increases, demonstrating scalability. These findings highlight the potential of decentralized, goal-driven MARL to support effective coordination in realistic multi-vehicle systems operating across diverse domains.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11992
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Goal-Oriented Multi-Agent Reinforcement Learning for Decentralized Agent Teams
Du, Hung
Nguyen, Hy
Thudumu, Srikanth
Vasa, Rajesh
Mouzakis, Kon
Multiagent Systems
Artificial Intelligence
Machine Learning
Connected and autonomous vehicles across land, water, and air must often operate in dynamic, unpredictable environments with limited communication, no centralized control, and partial observability. These real-world constraints pose significant challenges for coordination, particularly when vehicles pursue individual objectives. To address this, we propose a decentralized Multi-Agent Reinforcement Learning (MARL) framework that enables vehicles, acting as agents, to communicate selectively based on local goals and observations. This goal-aware communication strategy allows agents to share only relevant information, enhancing collaboration while respecting visibility limitations. We validate our approach in complex multi-agent navigation tasks featuring obstacles and dynamic agent populations. Results show that our method significantly improves task success rates and reduces time-to-goal compared to non-cooperative baselines. Moreover, task performance remains stable as the number of agents increases, demonstrating scalability. These findings highlight the potential of decentralized, goal-driven MARL to support effective coordination in realistic multi-vehicle systems operating across diverse domains.
title Goal-Oriented Multi-Agent Reinforcement Learning for Decentralized Agent Teams
topic Multiagent Systems
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2511.11992