Multi-Agent RL
Learning coordination in multi-agent systems
Last updated: February 24, 2026
We work on multi-agent reinforcement learning (MARL) algorithms for coordinating agents in cooperative tasks, such as search-and-rescue, surveillance missions, and warehouse robotics.
We work on co-designing multi-agent decision policies and the communication network that supports them. We also focus on addressing multi-agent credit assignment, a fundamental problem in MARL where agents must figure out which agent’s action contributed to a received reward.
Relevant publications
This work was funded in part by ARL W911NF2020184, NASA 80NSSC23M0221, and ONR N00014-20-1-2249.
