Publications: Multi-agent Coordination via Flow Matching, etc.; Patents: Method and Apparatus for Inferring Stochastic Driving Characteristic of a Vehicle, etc.; Awards: UT Austin Engineering Fellowship, AI Intensive Program at Carnegie Mellon University Scholarship, Future Industrial Talent Scholarship, etc.
Research Experience
Collaborated with Prof. Ding Zhao in the Safe AI Lab at CMU, with Prof. Minhae Kwon in BMIL, and with Prof. Sangsoo Kim in the Post-genome Informatics Lab at Soongsil University.
Education
PhD student at the University of Texas at Austin, supervised by Prof. Amy Zhang; previously collaborated with Prof. Ding Zhao at CMU, Prof. Minhae Kwon, and Prof. Sangsoo Kim at Soongsil University, South Korea.
Background
Research interests: applicability of reinforcement learning (RL) methods in practical and realistic settings, particularly in multi-agent, open-ended, and robotics settings. Specializes in multi-agent RL, representation learning, and offline-online RL.
Miscellany
Personal ethos: Speak truth, amid echoing scorn. Embrace adventure, born of conviction. Take responsibility, without retreat.