Embodied, Intelligent Communication for Multi-Agent Cooperation
Keywords:Reinforcement Learning, Multi-Agent Systems, Collaborative Decision-Making, Communication And Teaming, Learning From Demonstration
AbstractHigh-performing human teams leverage intelligent and efficient communication and coordination strategies to collaboratively maximize their joint utility. Inspired by teaming behaviors among humans, I seek to develop computational methods for synthesizing intelligent communication and coordination strategies for collaborative multi-robot systems. I leverage both classical model-based control and planning approaches as well as data-driven methods such as Multi-Agent Reinforcement Learning (MARL) to provide several contributions towards enabling emergent cooperative teaming behavior across both homogeneous and heterogeneous (including agents with different capabilities) robot teams.
How to Cite
Seraj, E. (2023). Embodied, Intelligent Communication for Multi-Agent Cooperation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16135-16136. https://doi.org/10.1609/aaai.v37i13.26928
AAAI Doctoral Consortium Track