Uncertainty-driven state space exploration for reinforcement learning강화 학습을 위한 불확실성 기반 상태 공간 탐색 알고리즘

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 494
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorLee, Sang Wan-
dc.contributor.advisor이상완-
dc.contributor.advisorJeong, Jae Seung-
dc.contributor.advisor정재승-
dc.contributor.authorAn, Su Jin-
dc.date.accessioned2018-06-20T06:17:32Z-
dc.date.available2018-06-20T06:17:32Z-
dc.date.issued2017-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=718757&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/243002-
dc.description학위논문(석사) - 한국과학기술원 : 뇌인지공학프로그램, 2017.8,[iii, 43 p. :]-
dc.description.abstractMetacognition is seen as the human’s capability to introspect their thought process and report their level of uncertainty/confidence in the course of learning. The metacognitive ability can be extremely useful in guiding behaviour during learning, in deciding whether to explore a new alternative or stick with the current one. In the past few years, the neuroscientific community has made some progress in understanding the neural basis of uncertainty/confidence representation. However, little is known about how uncertainty/confidence arises at the computational level during reinforcement learning. Here we propose to combine machine learning with behavioural data to characterise the exact computational steps that underlie the psychological construction of uncertainty during learning in complex environments, also aim to design a formal model for human’s state space learning process based on metacognition. The central aim of this work is to provide a mechanistic understanding of how uncertainty is constructed at the algorithmic level by the human brain and how it is used to drive learning.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectLearning▼aUncertainty▼aMetacognition▼aExploration-Exploitation dilemma▼aDecision making-
dc.subject학습▼a불확실성▼a메타 인지▼aExploration-Exploitation dilemma▼a의사 결정-
dc.titleUncertainty-driven state space exploration for reinforcement learning-
dc.title.alternative강화 학습을 위한 불확실성 기반 상태 공간 탐색 알고리즘-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :뇌인지공학프로그램,-
dc.contributor.alternativeauthor안수진-
Appears in Collection
BiS-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