Inverse reinforcement learning in partially observable environments = 부분관찰환경에서의 역강화학습

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 365
  • Download : 0
Inverse reinforcement learning (IRL) is the problem of recovering the underlying reward function from the behavior of an expert. Most of the existing algorithms for IRL assume that the expert`s environment is modeled as a Markov decision process (MDP), although they should be able to handle partially observable settings in order to widen the applicability to more realistic scenarios. In this paper, we present an extension of the classical IRL algorithm by Ng and Russell to partially observable environments. We discuss technical issues and challenges, and present the experimental results on some of the benchmark partially observable domains.
Advisors
Kim, Kee-Eungresearcher김기응researcher
Description
한국과학기술원 : 전산학전공,
Publisher
한국과학기술원
Issue Date
2009
Identifier
327349/325007  / 020083539
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전산학전공, 2009. 8., [ v, 36 p. ]

Keywords

Machine Learning.; Reinforcement Learning.; Partially Observable Markov Decision Processes(POMDPs).; Inverse Reinforcement Learning.; 기계학습.; 강화학습.; 부분관찰마르코프의사결정과정.; 역강화학습.; Machine Learning.; Reinforcement Learning.; Partially Observable Markov Decision Processes(POMDPs).; Inverse Reinforcement Learning.; 기계학습.; 강화학습.; 부분관찰마르코프의사결정과정.; 역강화학습.

URI
http://hdl.handle.net/10203/34884
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=327349&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