- 일시: 2025년 9월 1일(월) 오후 1시 30분
- 연사: 김우준 Postdoctoral Fellow(Carnegie Mellon University)
- 제목: Toward Coordinated Intelligence for the Real World
- ABSTRACT
The real world is inherently multi-agent, consisting
of numerous entities that must interact and coordinate in complex, dynamic
environments. Achieving effective operation in such settings requires
coordinated intelligence, where agents not only coordinate effectively but also
address practical challenges including scalability, robustness, and safety.
This talk will present methods for enhancing coordination and tackling these
challenges in the context of multi-agent deep reinforcement learning, and will showcase
applications to robotics, particularly focusing on robotic information
gathering.
- BIOGRAPHY
Dr.
Woojun Kim is a Postdoctoral Fellow at the Robotics Institute, Carnegie Mellon
University. He earned his Ph.D. in Electrical Engineering from KAIST, where his
research focused on multi-agent reinforcement learning. His current work
emphasizes coordination, scalability, robustness, and safe real-world
deployment, including applications to robotics. He has published in top machine
learning venues such as NeurIPS, ICML, and ICLR, as well as leading robotics
conferences including ICRA and CoRL. His work has been recognized with multiple
honors, including the Best Paper Award at the GenAI-HRI Workshop, RSS 2025, and
Best Conference Paper Finalist at ICRA 2025.
- 주관: 남창주 교수 연구실