Real-time heuristic search with reward shaping for bayesian reinforcement learning보상함수 조형을 적용한 베이지안 강화학습 휴리스틱 서치 알고리즘

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 597
  • Download : 0
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.
Advisors
Kim, Kee-Eungresearcher김기응
Description
한국과학기술원 : 전산학과,
Publisher
한국과학기술원
Issue Date
2014
Identifier
592444/325007  / 020124393
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전산학과, 2014.8, [ iv, 23p ]

Keywords

Heuristic Search; 보상함수 조형; 베이지안 강화학습; 휴리스틱 서치; Bayesian Reinforcement Learning; Reward Shaping

URI
http://hdl.handle.net/10203/196859
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=592444&flag=dissertation
Appears in Collection
CS-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