DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Shin, Jinwoo | - |
dc.contributor.advisor | 신진우 | - |
dc.contributor.author | Ahn, Sungsoo | - |
dc.date.accessioned | 2022-04-21T19:34:00Z | - |
dc.date.available | 2022-04-21T19:34:00Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=956662&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/295660 | - |
dc.description | 학위논문(박사) - 한국과학기술원 : 전기및전자공학부, 2021.2,[iv, 49 p. :] | - |
dc.description.abstract | Recently, deep reinforcement learning (DRL) framework has gained considerable attention as a new approach to solve combinatorial optimization problems which appear ubiquitously in various scientific fields. We propose to improve the existing DRL frameworks by considering the combinatorial nature of the problems. Specifically, we focus on two important applications with overwhelming difficulties for the current DRL framework: (1) the maximum independent set problem where the number of decisions to be made is prohibitively large, and (2) the molecular optimization problem which requires a vast amount of exploration. To this end, we draw inspirations from the traditional domain-specific algorithms for efficiently exploring the solution space. Namely, we show that existing DRL frameworks can be improved by (1) allowing the DRL agent to decide multiple variables at once and (2) using exploration operators that modify the existing candidate solutions. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | deep reinforcement learning▼acombinatorial optimization▼amaximum independent set▼amolecular optimization▼adrug discovery | - |
dc.subject | 심층 강화 학습▼a조합 최적화▼a최대 독립 집합▼a분자 구조 최적화▼a신약 제조 | - |
dc.title | Scaling deep reinforcement learning to large combinatorial optimization | - |
dc.title.alternative | 대형 조합 최적화를 위한 강화 학습 | - |
dc.type | Thesis(Ph.D) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 안성수 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.