Data augmentation for learning to play in text-based games텍스트 게임에서의 일반화를 위한 데이터 증강 연구

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 91
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorKim, Jinhyeon-
dc.date.accessioned2023-06-22T19:31:10Z-
dc.date.available2023-06-22T19:31:10Z-
dc.date.issued2022-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1000343&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/308176-
dc.description학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2022.2,[iv, 19 p. :]-
dc.description.abstractText-based game is an instance of partially observable environment where the observation and action are in the form of natural language. Generalizing in text-based games serves as a useful stepping-stone towards reinforcement learning (RL) agent with generic linguistic ability. Prior works on generalization in RL often applied data augmentation techniques, but none of them focused on text-based games. We propose a novel data augmentation technique for text-based games, Transition-Matching Permutation, where we identify phrase permutations that match as many transitions in the trajectory data. Applying this technique resulted in the state-of-the-art performance in a procedurally generated TextWorld's Cooking Game benchmark.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subject텍스트 게임▼a자연어 처리▼a강화 학습▼a데이터 증강-
dc.subjectText-based game▼aNatural language processing▼aReinforcement learning▼aData augmentation-
dc.titleData augmentation for learning to play in text-based games-
dc.title.alternative텍스트 게임에서의 일반화를 위한 데이터 증강 연구-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :김재철AI대학원,-
dc.contributor.alternativeauthor김진현-
Appears in Collection
AI-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0