Cross-domain imitation learning with feature synthesis특성합성을 이용한 교차영역 모방학습

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 146
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorSung, Youngchul-
dc.contributor.advisor성영철-
dc.contributor.authorChoi, Sungho-
dc.date.accessioned2021-05-13T19:34:27Z-
dc.date.available2021-05-13T19:34:27Z-
dc.date.issued2020-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=911414&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/284784-
dc.description학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2020.2,[ii, 25 p. :]-
dc.description.abstractThis study suggested a cross-domain imitation learning method where the agent in one domain follows the behavior of an expert in another domain without accessing any reward function. One common method is to extract domain-independent feature vectors from inputs and determine how well the agent is trained. However, due to the difference between two domains, the behavior of the agent cannot be compared appropriately with that of the expert regardless of its degree of training. To overcome this problem, we extracted two feature vectors from each input-
dc.description.abstractone contained only domain information and the other contained only policy expertness information. The expert data in target-domain can be produced by combining the target-domain feature vector and the expert-policy feature vector. The proposed method showed improved performance in several environments with domain discrepancies. From this study, we can expect to alleviate the difficulties of collecting demonstrations and increase the efficiency of training agents using imitation learning.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectreinforcement learning▼aimitation learning▼adomain adaptation▼afeature synthesis▼aadversarial training-
dc.subject강화학습▼a모방학습▼a영역적응▼a특성합성▼a적대적 학습-
dc.titleCross-domain imitation learning with feature synthesis-
dc.title.alternative특성합성을 이용한 교차영역 모방학습-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :전기및전자공학부,-
dc.contributor.alternativeauthor최성호-
Appears in Collection
EE-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