I am a master student in KAIST Graduate school of AI, advised by Prof. Kimin Lee.
I am interested in developing a safe and proficient decision-making agent in real-world(e.g., robots). To this end, I aim to develop a method that can extract behavioral rules from existing data efficiently and help the agent continuously self-improve. Relevant topics include imitation learning on human data and developing scalable reinforcement learning (RL) algorithms that can work both on/offline.
Relevant keywords include imitation learning, hierarchical RL, explorations in RL, and robot learning.
2024
Understanding Impact of Human Feedback via Influence Functions
Taywon Min, Haeone Lee, Hanho Ryu, and 2 more authors
@article{lee2024influence,title={Understanding Impact of Human Feedback via Influence Functions},author={Min, Taywon and Lee, Haeone and Ryu, Hanho and Kwon, Yongchan and Lee, Kimin},journal={In submission},year={2024},}
Benchmarking Mobile Device Control Agents across Diverse Configurations
Juyong Lee, Taywon Min, Minyong An, and 4 more authors
ICLR 2024 Workshop on Generative Models for Decision Making., 2024
@article{lee2024benchmarking,title={Benchmarking Mobile Device Control Agents across Diverse Configurations},author={Lee, Juyong and Min, Taywon and An, Minyong and Hahm, Dongyoon and Lee, Haeone and Kim, Changyeon and Lee, Kimin},journal={ICLR 2024 Workshop on Generative Models for Decision Making.},year={2024}}
