Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952902960> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2952902960 endingPage "290" @default.
- W2952902960 startingPage "283" @default.
- W2952902960 abstract "A central problem in artificial intelligence is that of planning to maximize future reward under uncertainty in a partially observable environment. In this paper we propose and demonstrate a novel algorithm which accurately learns a model of such an environment directly from sequences of action-observation pairs. We then close the loop from observations to actions by planning in the learned model and recovering a policy which is near-optimal in the original environment. Specifically, we present an efficient and statistically consistent spectral algorithm for learning the parameters of a Predictive State Representation (PSR). We demonstrate the algorithm by learning a model of a simulated high-dimensional, vision-based mobile robot planning task, and then perform approximate point-based planning in the learned PSR. Analysis of our results shows that the algorithm learns a state space which efficiently captures the essential features of the environment. This representation allows accurate prediction with a small number of parameters, and enables successful and efficient planning." @default.
- W2952902960 created "2019-06-27" @default.
- W2952902960 creator A5004984954 @default.
- W2952902960 creator A5012830032 @default.
- W2952902960 creator A5052552981 @default.
- W2952902960 date "2011-08-05" @default.
- W2952902960 modified "2023-09-24" @default.
- W2952902960 title "Closing the Learning-Planning Loop with Predictive State Representations" @default.
- W2952902960 cites W1484113995 @default.
- W2952902960 cites W1486632395 @default.
- W2952902960 cites W1499044922 @default.
- W2952902960 cites W1507852408 @default.
- W2952902960 cites W1532688806 @default.
- W2952902960 cites W1540337045 @default.
- W2952902960 cites W1565405003 @default.
- W2952902960 cites W1580557482 @default.
- W2952902960 cites W1583380718 @default.
- W2952902960 cites W1972251511 @default.
- W2952902960 cites W1987974668 @default.
- W2952902960 cites W2011418219 @default.
- W2952902960 cites W2042830238 @default.
- W2952902960 cites W2058853801 @default.
- W2952902960 cites W2099873296 @default.
- W2952902960 cites W2110962519 @default.
- W2952902960 cites W2123542217 @default.
- W2952902960 cites W2129905273 @default.
- W2952902960 cites W2144416853 @default.
- W2952902960 cites W2149960632 @default.
- W2952902960 cites W2154384352 @default.
- W2952902960 cites W2158282517 @default.
- W2952902960 cites W2161139607 @default.
- W2952902960 cites W2163126463 @default.
- W2952902960 cites W2171627535 @default.
- W2952902960 cites W2569025259 @default.
- W2952902960 cites W2949313516 @default.
- W2952902960 doi "https://doi.org/10.7551/mitpress/9123.003.0040" @default.
- W2952902960 hasPublicationYear "2011" @default.
- W2952902960 type Work @default.
- W2952902960 sameAs 2952902960 @default.
- W2952902960 citedByCount "6" @default.
- W2952902960 countsByYear W29529029602014 @default.
- W2952902960 countsByYear W29529029602015 @default.
- W2952902960 countsByYear W29529029602016 @default.
- W2952902960 countsByYear W29529029602017 @default.
- W2952902960 crossrefType "book-chapter" @default.
- W2952902960 hasAuthorship W2952902960A5004984954 @default.
- W2952902960 hasAuthorship W2952902960A5012830032 @default.
- W2952902960 hasAuthorship W2952902960A5052552981 @default.
- W2952902960 hasBestOaLocation W29529029602 @default.
- W2952902960 hasConcept C11413529 @default.
- W2952902960 hasConcept C114614502 @default.
- W2952902960 hasConcept C154945302 @default.
- W2952902960 hasConcept C17744445 @default.
- W2952902960 hasConcept C184670325 @default.
- W2952902960 hasConcept C199539241 @default.
- W2952902960 hasConcept C2775924081 @default.
- W2952902960 hasConcept C2778775528 @default.
- W2952902960 hasConcept C33923547 @default.
- W2952902960 hasConcept C41008148 @default.
- W2952902960 hasConcept C47446073 @default.
- W2952902960 hasConcept C48103436 @default.
- W2952902960 hasConceptScore W2952902960C11413529 @default.
- W2952902960 hasConceptScore W2952902960C114614502 @default.
- W2952902960 hasConceptScore W2952902960C154945302 @default.
- W2952902960 hasConceptScore W2952902960C17744445 @default.
- W2952902960 hasConceptScore W2952902960C184670325 @default.
- W2952902960 hasConceptScore W2952902960C199539241 @default.
- W2952902960 hasConceptScore W2952902960C2775924081 @default.
- W2952902960 hasConceptScore W2952902960C2778775528 @default.
- W2952902960 hasConceptScore W2952902960C33923547 @default.
- W2952902960 hasConceptScore W2952902960C41008148 @default.
- W2952902960 hasConceptScore W2952902960C47446073 @default.
- W2952902960 hasConceptScore W2952902960C48103436 @default.
- W2952902960 hasLocation W29529029601 @default.
- W2952902960 hasLocation W29529029602 @default.
- W2952902960 hasLocation W29529029603 @default.
- W2952902960 hasOpenAccess W2952902960 @default.
- W2952902960 hasPrimaryLocation W29529029601 @default.
- W2952902960 hasRelatedWork W1980169972 @default.
- W2952902960 hasRelatedWork W2118251449 @default.
- W2952902960 hasRelatedWork W2269482810 @default.
- W2952902960 hasRelatedWork W2346600750 @default.
- W2952902960 hasRelatedWork W2363585414 @default.
- W2952902960 hasRelatedWork W2369068860 @default.
- W2952902960 hasRelatedWork W3087916668 @default.
- W2952902960 hasRelatedWork W3154158938 @default.
- W2952902960 hasRelatedWork W2136893344 @default.
- W2952902960 hasRelatedWork W2513109100 @default.
- W2952902960 isParatext "false" @default.
- W2952902960 isRetracted "false" @default.
- W2952902960 magId "2952902960" @default.
- W2952902960 workType "book-chapter" @default.