Multi-Agent Navigation in Dynamic Environments

We study the problem of coordinating teams of vehicles with limited sensing and communication to navigate in environments with dynamic (adversarial) and static obstacles using graph neural networks and multi-agent reinforcement learning.

Publications:

1. InforMARL: Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation. (ICML 2023)
2. Transfer Learning for Space Traffic Management. (L4DC 2023)
3. Cooperation and Fairness in Multi-Agent Reinforcement Learning. (ACM Journal on Autonomous Transportation Systems)

People

Siddharth Nayak, Sydney Dolan, Jasmine Jerry Aloor, Victor Qin, Geoffrey Ding, Kenneth Choi, Wenqi Ding, Karthik Gopalakrishnan, Hamsa Balakrishnan

---