DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 김기응 | - |
dc.contributor.author | Kim, Sungyoon | - |
dc.contributor.author | 김성윤 | - |
dc.date.accessioned | 2024-07-25T19:30:43Z | - |
dc.date.available | 2024-07-25T19:30:43Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1045715&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/320527 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2023.8,[iii, 19 p. :] | - |
dc.description.abstract | This paper discusses an approach to offline Goal-Conditioned Reinforcement Learning(GCRL) using a diffusion model. GCRL is a problem of learning policies that depend on given goals, and it is important to extract useful information from sparse reward signals. To address this, the proposed methodology introduces a planning-based approach using a conditional diffusion model to generate trajectories for taking actions. Specifically, a goal relabeling method is proposed to overcome sparse rewards, and a conditional diffusion model is tasked to generate trajectories that satisfy certain action value level. The proposed methodology demonstrates high performance in various GCRL experimental environments, as demonstrated through qualitative and quantitative evaluations. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 오프라인 목표지향 강화학습▼a디퓨전 모델▼a플래닝 | - |
dc.subject | Offline goal-conditioned reinforcement learning▼aDiffusion model▼aPlanning | - |
dc.title | Value-instilled diffusion for offline goal-conditioned reinforcement learning | - |
dc.title.alternative | 오프라인 목표조건부 강화학습을 위한 가치관입 디퓨전 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | Kim, Kee-Eung | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.