Matches in SemOpenAlex for { <https://semopenalex.org/work/W30507863> ?p ?o ?g. }
- W30507863 endingPage "743" @default.
- W30507863 startingPage "738" @default.
- W30507863 abstract "We introduce an approach to autonomously creating state space abstractions for an online reinforcement learning agent using a relational representation. Our approach uses a tree-based function approximation derived from McCallum's [1995] UTree algorithm. We have extended this approach to use a relational representation where relational observations are represented by attributed graphs [McGovern et al., 2003]. We address the challenges introduced by a relational representation by using stochastic sampling to manage the search space [Srinivasan, 1999] and temporal sampling to manage autocorrelation [Jensen and Neville, 2002]. Relational UTree incorporates Iterative Tree Induction [Utgoff et al., 1997] to allow it to adapt to changing environments. We empirically demonstrate that Relational UTree performs better than similar relational learning methods [Finney et al., 2002; Driessens et al., 2001] in a blocks world domain. We also demonstrate that Relational UTree can learn to play a sub-task of the game of Go called Tsume-Go [Ramon et al., 2001]." @default.
- W30507863 created "2016-06-24" @default.
- W30507863 creator A5005273621 @default.
- W30507863 creator A5070181594 @default.
- W30507863 date "2007-01-06" @default.
- W30507863 modified "2023-09-24" @default.
- W30507863 title "Utile distinctions for relational reinforcement learning" @default.
- W30507863 cites W115717799 @default.
- W30507863 cites W1495603628 @default.
- W30507863 cites W1515851193 @default.
- W30507863 cites W1537801732 @default.
- W30507863 cites W1583380718 @default.
- W30507863 cites W1640646391 @default.
- W30507863 cites W1666347389 @default.
- W30507863 cites W2119828730 @default.
- W30507863 cites W2121863487 @default.
- W30507863 cites W2124125910 @default.
- W30507863 cites W2133632100 @default.
- W30507863 cites W2138745909 @default.
- W30507863 cites W2139544716 @default.
- W30507863 cites W2154441654 @default.
- W30507863 cites W2167945827 @default.
- W30507863 cites W2168359464 @default.
- W30507863 cites W2314731117 @default.
- W30507863 cites W2341171179 @default.
- W30507863 cites W2396715201 @default.
- W30507863 cites W2521075165 @default.
- W30507863 cites W2521833123 @default.
- W30507863 cites W3020831056 @default.
- W30507863 cites W38340148 @default.
- W30507863 hasPublicationYear "2007" @default.
- W30507863 type Work @default.
- W30507863 sameAs 30507863 @default.
- W30507863 citedByCount "5" @default.
- W30507863 countsByYear W305078632013 @default.
- W30507863 countsByYear W305078632022 @default.
- W30507863 crossrefType "proceedings-article" @default.
- W30507863 hasAuthorship W30507863A5005273621 @default.
- W30507863 hasAuthorship W30507863A5070181594 @default.
- W30507863 hasConcept C105795698 @default.
- W30507863 hasConcept C106131492 @default.
- W30507863 hasConcept C113174947 @default.
- W30507863 hasConcept C119857082 @default.
- W30507863 hasConcept C124101348 @default.
- W30507863 hasConcept C134306372 @default.
- W30507863 hasConcept C140779682 @default.
- W30507863 hasConcept C154945302 @default.
- W30507863 hasConcept C162324750 @default.
- W30507863 hasConcept C17744445 @default.
- W30507863 hasConcept C177877439 @default.
- W30507863 hasConcept C187736073 @default.
- W30507863 hasConcept C199539241 @default.
- W30507863 hasConcept C2776359362 @default.
- W30507863 hasConcept C2780451532 @default.
- W30507863 hasConcept C31972630 @default.
- W30507863 hasConcept C33923547 @default.
- W30507863 hasConcept C40207289 @default.
- W30507863 hasConcept C41008148 @default.
- W30507863 hasConcept C5655090 @default.
- W30507863 hasConcept C72434380 @default.
- W30507863 hasConcept C80444323 @default.
- W30507863 hasConcept C94625758 @default.
- W30507863 hasConcept C97541855 @default.
- W30507863 hasConcept C99436015 @default.
- W30507863 hasConceptScore W30507863C105795698 @default.
- W30507863 hasConceptScore W30507863C106131492 @default.
- W30507863 hasConceptScore W30507863C113174947 @default.
- W30507863 hasConceptScore W30507863C119857082 @default.
- W30507863 hasConceptScore W30507863C124101348 @default.
- W30507863 hasConceptScore W30507863C134306372 @default.
- W30507863 hasConceptScore W30507863C140779682 @default.
- W30507863 hasConceptScore W30507863C154945302 @default.
- W30507863 hasConceptScore W30507863C162324750 @default.
- W30507863 hasConceptScore W30507863C17744445 @default.
- W30507863 hasConceptScore W30507863C177877439 @default.
- W30507863 hasConceptScore W30507863C187736073 @default.
- W30507863 hasConceptScore W30507863C199539241 @default.
- W30507863 hasConceptScore W30507863C2776359362 @default.
- W30507863 hasConceptScore W30507863C2780451532 @default.
- W30507863 hasConceptScore W30507863C31972630 @default.
- W30507863 hasConceptScore W30507863C33923547 @default.
- W30507863 hasConceptScore W30507863C40207289 @default.
- W30507863 hasConceptScore W30507863C41008148 @default.
- W30507863 hasConceptScore W30507863C5655090 @default.
- W30507863 hasConceptScore W30507863C72434380 @default.
- W30507863 hasConceptScore W30507863C80444323 @default.
- W30507863 hasConceptScore W30507863C94625758 @default.
- W30507863 hasConceptScore W30507863C97541855 @default.
- W30507863 hasConceptScore W30507863C99436015 @default.
- W30507863 hasLocation W305078631 @default.
- W30507863 hasOpenAccess W30507863 @default.
- W30507863 hasPrimaryLocation W305078631 @default.
- W30507863 hasRelatedWork W1526052557 @default.
- W30507863 hasRelatedWork W1826836734 @default.
- W30507863 hasRelatedWork W2097772949 @default.
- W30507863 hasRelatedWork W2134100786 @default.
- W30507863 hasRelatedWork W2154441654 @default.
- W30507863 hasRelatedWork W2320781667 @default.