Matches in SemOpenAlex for { <https://semopenalex.org/work/W2085836402> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2085836402 endingPage "2653" @default.
- W2085836402 startingPage "2632" @default.
- W2085836402 abstract "In this paper a new framework, called Compressive Kernelized Reinforcement Learning (CKRL), for computing near-optimal policies in sequential decision making with uncertainty is proposed via incorporating the non-adaptive data-independent Random Projections and nonparametric Kernelized Least-squares Policy Iteration (KLSPI). Random Projections are a fast, non-adaptive dimensionality reduction framework in which high-dimensionality data is projected onto a random lower-dimension subspace via spherically random rotation and coordination sampling. KLSPI introduce kernel trick into the LSPI framework for Reinforcement Learning, often achieving faster convergence and providing automatic feature selection via various kernel sparsification approaches. In this approach, policies are computed in a low-dimensional subspace generated by projecting the high-dimensional features onto a set of random basis. We first show how Random Projections constitute an efficient sparsification technique and how our method often converges faster than regular LSPI, while at lower computational costs. Theoretical foundation underlying this approach is a fast approximation of Singular Value Decomposition (SVD). Finally, simulation results are exhibited on benchmark MDP domains, which confirm gains both in computation time and in performance in large feature spaces." @default.
- W2085836402 created "2016-06-24" @default.
- W2085836402 creator A5028788431 @default.
- W2085836402 creator A5032106989 @default.
- W2085836402 creator A5065912071 @default.
- W2085836402 creator A5090815103 @default.
- W2085836402 date "2012-02-28" @default.
- W2085836402 modified "2023-09-26" @default.
- W2085836402 title "Intelligent Control of a Sensor-Actuator System via Kernelized Least-Squares Policy Iteration" @default.
- W2085836402 cites W1507222174 @default.
- W2085836402 cites W1971713783 @default.
- W2085836402 cites W2072931156 @default.
- W2085836402 cites W2118556122 @default.
- W2085836402 cites W2153290280 @default.
- W2085836402 cites W2168973828 @default.
- W2085836402 cites W4250955649 @default.
- W2085836402 doi "https://doi.org/10.3390/s120302632" @default.
- W2085836402 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/3376585" @default.
- W2085836402 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/22736969" @default.
- W2085836402 hasPublicationYear "2012" @default.
- W2085836402 type Work @default.
- W2085836402 sameAs 2085836402 @default.
- W2085836402 citedByCount "1" @default.
- W2085836402 countsByYear W20858364022012 @default.
- W2085836402 crossrefType "journal-article" @default.
- W2085836402 hasAuthorship W2085836402A5028788431 @default.
- W2085836402 hasAuthorship W2085836402A5032106989 @default.
- W2085836402 hasAuthorship W2085836402A5065912071 @default.
- W2085836402 hasAuthorship W2085836402A5090815103 @default.
- W2085836402 hasBestOaLocation W20858364021 @default.
- W2085836402 hasConcept C111030470 @default.
- W2085836402 hasConcept C11413529 @default.
- W2085836402 hasConcept C114614502 @default.
- W2085836402 hasConcept C126255220 @default.
- W2085836402 hasConcept C13280743 @default.
- W2085836402 hasConcept C154945302 @default.
- W2085836402 hasConcept C185798385 @default.
- W2085836402 hasConcept C205649164 @default.
- W2085836402 hasConcept C22789450 @default.
- W2085836402 hasConcept C2777036070 @default.
- W2085836402 hasConcept C32834561 @default.
- W2085836402 hasConcept C33923547 @default.
- W2085836402 hasConcept C41008148 @default.
- W2085836402 hasConcept C70518039 @default.
- W2085836402 hasConcept C74193536 @default.
- W2085836402 hasConcept C97541855 @default.
- W2085836402 hasConceptScore W2085836402C111030470 @default.
- W2085836402 hasConceptScore W2085836402C11413529 @default.
- W2085836402 hasConceptScore W2085836402C114614502 @default.
- W2085836402 hasConceptScore W2085836402C126255220 @default.
- W2085836402 hasConceptScore W2085836402C13280743 @default.
- W2085836402 hasConceptScore W2085836402C154945302 @default.
- W2085836402 hasConceptScore W2085836402C185798385 @default.
- W2085836402 hasConceptScore W2085836402C205649164 @default.
- W2085836402 hasConceptScore W2085836402C22789450 @default.
- W2085836402 hasConceptScore W2085836402C2777036070 @default.
- W2085836402 hasConceptScore W2085836402C32834561 @default.
- W2085836402 hasConceptScore W2085836402C33923547 @default.
- W2085836402 hasConceptScore W2085836402C41008148 @default.
- W2085836402 hasConceptScore W2085836402C70518039 @default.
- W2085836402 hasConceptScore W2085836402C74193536 @default.
- W2085836402 hasConceptScore W2085836402C97541855 @default.
- W2085836402 hasIssue "3" @default.
- W2085836402 hasLocation W20858364021 @default.
- W2085836402 hasLocation W20858364022 @default.
- W2085836402 hasLocation W20858364023 @default.
- W2085836402 hasLocation W20858364024 @default.
- W2085836402 hasLocation W20858364025 @default.
- W2085836402 hasOpenAccess W2085836402 @default.
- W2085836402 hasPrimaryLocation W20858364021 @default.
- W2085836402 hasRelatedWork W2014040967 @default.
- W2085836402 hasRelatedWork W2080754616 @default.
- W2085836402 hasRelatedWork W2089497633 @default.
- W2085836402 hasRelatedWork W2245231753 @default.
- W2085836402 hasRelatedWork W2541308381 @default.
- W2085836402 hasRelatedWork W2624745934 @default.
- W2085836402 hasRelatedWork W2952300832 @default.
- W2085836402 hasRelatedWork W3035891470 @default.
- W2085836402 hasRelatedWork W3102427307 @default.
- W2085836402 hasRelatedWork W4287755309 @default.
- W2085836402 hasVolume "12" @default.
- W2085836402 isParatext "false" @default.
- W2085836402 isRetracted "false" @default.
- W2085836402 magId "2085836402" @default.
- W2085836402 workType "article" @default.