JunHyeok Oh

MS student, Korea University

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 6

1 paper

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Prior-Guided Diffusion Planning for Offline Reinforcement Learning

#300 · Donghyeon Ki, JunHyeok Oh, Seong-Woong Shim, Byung-Jun Lee

We propose Prior Guidance, a novel guided sampling framework for diffusion-based planners in offline RL that replaces the standard Gaussian prior of a behavior-cloned diffusion model with a learnable distribution.