影响力指数

62.92/100

前 4%

全站排名 #2,595

发表论文9 篇

平均评分6.2

年均产出3.0 篇/年

Jeonghye Kim

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

研究方向

Reinforcement Learning

Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization

ICLR 2026Poster

Constrained Diffusion Policy Optimization for Offline Reinforcement Learning

ICLR 2026Withdrawn

Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data

ICML 2025Spotlight

Online Pre-Training for Offline-to-Online Reinforcement Learning

ICML 2025Poster

ARS: Adaptive Reward Scaling for Multi-Task Reinforcement Learning

ICML 2025Poster

Online Pre-Training for Offline-to-Online Reinforcement Learning

ICLR 2025Rejected

Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data

ICLR 2025Rejected

合作者 (20)

博士导师8 篇