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

2025/11/15 by Hung Du, Hy Nguyen, Du, Hung +7
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Autonomous Vehicle Technology and Safety #Autonomous agent #Collision avoidance #Control (management) #Distributed Control Multi-Agent Systems #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multi-agent system #Multiagent Systems (cs.MA) #Reinforcement Learning in Robotics #Reinforcement learning #Task (project management) #Task analysis #Visibility

paper · pdf · doi:10.48550/arxiv.2511.11992

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/11/15 · openalex created_date 2025/11/19 · openalex updated_date 2026/08/05

Abstract

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.

Citations

• A Survey on Context-Aware Multi-Agent Systems: Techniques, Challenges and Future Directions
• Cautiously-Optimistic Knowledge Sharing for Cooperative Multi-Agent Reinforcement Learning
• Learn to Follow: Decentralized Lifelong Multi-agent Pathfinding via Planning and Learning
• Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation
• The Complexity of Markov Equilibrium in Stochastic Games
• GCS: Graph-based Coordination Strategy for Multi-Agent Reinforcement Learning
• V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL
• Learning to Coordinate via Multiple Graph Neural Networks
• Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?
• When2com: Multi-Agent Perception via Communication Graph Grouping
• Who2com: Collaborative Perception via Learnable Handshake Communication
• A Comprehensive Survey on Transfer Learning
• A Comprehensive Survey on Transfer Learning
• Deep Coordination Graphs
• Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control
• Learning Attentional Communication for Multi-Agent Cooperation
• Asynchronous Methods for Deep Reinforcement Learning
• Continuous control with deep reinforcement learning

Related

• Decentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent Advances
• HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging
• An Introduction to Multi-Agent Reinforcement Learning and Review of its Application to Autonomous Mobility
• Advances in Multi-agent Reinforcement Learning: Persistent Autonomy and Robot Learning Lab Report 2024
• Multi-Agent Reinforcement Learning in Intelligent Transportation Systems: A Comprehensive Survey