Matches in SemOpenAlex for { <https://semopenalex.org/work/W1985756506> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W1985756506 endingPage "835" @default.
- W1985756506 startingPage "821" @default.
- W1985756506 abstract "Recent researches on automatic skill acquisition in reinforcement learning have focused on subgoal discovery methods. Among them, algorithms based on graph partitioning have achieved higher performance. In this paper, we propose a new automatic skill acquisition framework based on graph partitioning approach. The main steps of this framework are identifying subgoals and discovering useful skills. We propose two subgoal discovery algorithms, which use spectral analysis on the transition graph of the learning agent. The first proposed algorithm, incorporates k′-means algorithm with spectral clustering. In the second algorithm, eigenvector centrality measure is utilized and options are discovered. Moreover, we propose an algorithm for pruning useless options, which cause additional costs for the learning agent. The experimental results on various problems show significant improvement in the learning performance of the agent." @default.
- W1985756506 created "2016-06-24" @default.
- W1985756506 creator A5039326288 @default.
- W1985756506 creator A5089030033 @default.
- W1985756506 date "2013-08-01" @default.
- W1985756506 modified "2023-09-23" @default.
- W1985756506 title "A novel graphical approach to automatic abstraction in reinforcement learning" @default.
- W1985756506 cites W1536990779 @default.
- W1985756506 cites W1544120923 @default.
- W1985756506 cites W1549884255 @default.
- W1985756506 cites W1562016390 @default.
- W1985756506 cites W1600813180 @default.
- W1985756506 cites W1988821219 @default.
- W1985756506 cites W2034342292 @default.
- W1985756506 cites W2082973084 @default.
- W1985756506 cites W2105833908 @default.
- W1985756506 cites W2109910161 @default.
- W1985756506 cites W2117686912 @default.
- W1985756506 cites W2118820208 @default.
- W1985756506 cites W2121517924 @default.
- W1985756506 cites W2125836634 @default.
- W1985756506 cites W2127048411 @default.
- W1985756506 cites W2131466408 @default.
- W1985756506 cites W2141559645 @default.
- W1985756506 cites W2151803317 @default.
- W1985756506 cites W2160808139 @default.
- W1985756506 cites W2161252410 @default.
- W1985756506 cites W32403112 @default.
- W1985756506 doi "https://doi.org/10.1016/j.robot.2013.04.010" @default.
- W1985756506 hasPublicationYear "2013" @default.
- W1985756506 type Work @default.
- W1985756506 sameAs 1985756506 @default.
- W1985756506 citedByCount "17" @default.
- W1985756506 countsByYear W19857565062014 @default.
- W1985756506 countsByYear W19857565062016 @default.
- W1985756506 countsByYear W19857565062017 @default.
- W1985756506 countsByYear W19857565062018 @default.
- W1985756506 countsByYear W19857565062019 @default.
- W1985756506 countsByYear W19857565062020 @default.
- W1985756506 countsByYear W19857565062023 @default.
- W1985756506 crossrefType "journal-article" @default.
- W1985756506 hasAuthorship W1985756506A5039326288 @default.
- W1985756506 hasAuthorship W1985756506A5089030033 @default.
- W1985756506 hasConcept C105611402 @default.
- W1985756506 hasConcept C108010975 @default.
- W1985756506 hasConcept C111472728 @default.
- W1985756506 hasConcept C119857082 @default.
- W1985756506 hasConcept C124101348 @default.
- W1985756506 hasConcept C124304363 @default.
- W1985756506 hasConcept C132525143 @default.
- W1985756506 hasConcept C138885662 @default.
- W1985756506 hasConcept C154945302 @default.
- W1985756506 hasConcept C41008148 @default.
- W1985756506 hasConcept C6557445 @default.
- W1985756506 hasConcept C73555534 @default.
- W1985756506 hasConcept C80444323 @default.
- W1985756506 hasConcept C86803240 @default.
- W1985756506 hasConcept C97541855 @default.
- W1985756506 hasConceptScore W1985756506C105611402 @default.
- W1985756506 hasConceptScore W1985756506C108010975 @default.
- W1985756506 hasConceptScore W1985756506C111472728 @default.
- W1985756506 hasConceptScore W1985756506C119857082 @default.
- W1985756506 hasConceptScore W1985756506C124101348 @default.
- W1985756506 hasConceptScore W1985756506C124304363 @default.
- W1985756506 hasConceptScore W1985756506C132525143 @default.
- W1985756506 hasConceptScore W1985756506C138885662 @default.
- W1985756506 hasConceptScore W1985756506C154945302 @default.
- W1985756506 hasConceptScore W1985756506C41008148 @default.
- W1985756506 hasConceptScore W1985756506C6557445 @default.
- W1985756506 hasConceptScore W1985756506C73555534 @default.
- W1985756506 hasConceptScore W1985756506C80444323 @default.
- W1985756506 hasConceptScore W1985756506C86803240 @default.
- W1985756506 hasConceptScore W1985756506C97541855 @default.
- W1985756506 hasIssue "8" @default.
- W1985756506 hasLocation W19857565061 @default.
- W1985756506 hasOpenAccess W1985756506 @default.
- W1985756506 hasPrimaryLocation W19857565061 @default.
- W1985756506 hasRelatedWork W1549839916 @default.
- W1985756506 hasRelatedWork W1986919318 @default.
- W1985756506 hasRelatedWork W2154303101 @default.
- W1985756506 hasRelatedWork W2170375089 @default.
- W1985756506 hasRelatedWork W2336900506 @default.
- W1985756506 hasRelatedWork W2991729049 @default.
- W1985756506 hasRelatedWork W3022038857 @default.
- W1985756506 hasRelatedWork W3157088924 @default.
- W1985756506 hasRelatedWork W3199608561 @default.
- W1985756506 hasRelatedWork W4319083788 @default.
- W1985756506 hasVolume "61" @default.
- W1985756506 isParatext "false" @default.
- W1985756506 isRetracted "false" @default.
- W1985756506 magId "1985756506" @default.
- W1985756506 workType "article" @default.