Multi-Agent Navigation in Dynamic Environments
![](https://aeroastro.mit.edu/wp-content/uploads/2022/11/Lab-DNM-marl-pic-446x446-c-default.jpg)
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:
- InforMARL: Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation. (ICML 2023)
- Transfer Learning for Space Traffic Management. (L4DC 2023)
People
Siddharth Nayak, Sydney Dolan, Jasmine Jerry Aloor, Allen Shtofenmakher, Victor Qin, Geoffrey Ding, Kenneth Choi, Wenqi Ding, Karthik Gopalakrishnan, Hamsa Balakrishnan