DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Kee-Eung | - |
dc.contributor.advisor | 김기응 | - |
dc.contributor.author | Kim, Hyeon-Eun | - |
dc.contributor.author | 김현은 | - |
dc.date.accessioned | 2015-04-23T06:16:06Z | - |
dc.date.available | 2015-04-23T06:16:06Z | - |
dc.date.issued | 2014 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=592444&flag=dissertation | - |
dc.identifier.uri | http://hdl.handle.net/10203/196859 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학과, 2014.8, [ iv, 23p ] | - |
dc.description.abstract | Bayesian reinforcement learning (BRL) provides a formal framework to optimally trading off exploration and exploitation in reinforcement learning. Unfortunately, it is generally intractable to find the Bayes-optimal behavior since the uncertainty in the model of the environment has to be taken into account. In this paper, we present a heuristic search approach to the model-based BRL. In addition, we present potential-based reward shaping for model-based BRL that makes the search more effective. The potential functions we propose are domain-independent in the sense that they do not require any knowledge about the actual environment model. We show that the proposed potential functions generally improve the quality of search, enabling our heuristic search algorithm to outperform state-of-the-art BRL algorithms in standard benchmark domains. | eng |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Heuristic Search | - |
dc.subject | 보상함수 조형 | - |
dc.subject | 베이지안 강화학습 | - |
dc.subject | 휴리스틱 서치 | - |
dc.subject | Bayesian Reinforcement Learning | - |
dc.subject | Reward Shaping | - |
dc.title | Real-time heuristic search with reward shaping for bayesian reinforcement learning | - |
dc.title.alternative | 보상함수 조형을 적용한 베이지안 강화학습 휴리스틱 서치 알고리즘 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 592444/325007 | - |
dc.description.department | 한국과학기술원 : 전산학과, | - |
dc.identifier.uid | 020124393 | - |
dc.contributor.localauthor | Kim, Kee-Eung | - |
dc.contributor.localauthor | 김기응 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.