Yongsik Lee

PhD student@Korea Advanced Institute of Science & Technology·韩国·OpenReview

研究方向

LLM Agent · RLHF · Alignment · Preference-based Reinforcement Learning (PbRL) · Reinforcement Learning (RL) · Multi-Agent Reinforcement Learning (MARL)

发表论文（3 篇）

6.3

MA$^2$E: Addressing Partial Observability in Multi-Agent Reinforcement Learning with Masked Auto-Encoder

合作者 (6)