Matches in SemOpenAlex for { <https://semopenalex.org/work/W2953329907> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2953329907 abstract "Direct contextual policy search methods learn to improve policy parameters and simultaneously generalize these parameters to different context or task variables. However, learning from high-dimensional context variables, such as camera images, is still a prominent problem in many real-world tasks. A naive application of unsupervised dimensionality reduction methods to the context variables, such as principal component analysis, is insufficient as task-relevant input may be ignored. In this paper, we propose a contextual policy search method in the model-based relative entropy stochastic search framework with integrated dimensionality reduction. We learn a model of the reward that is locally quadratic in both the policy parameters and the context variables. Furthermore, we perform supervised linear dimensionality reduction on the context variables by nuclear norm regularization. The experimental results show that the proposed method outperforms naive dimensionality reduction via principal component analysis and a state-of-the-art contextual policy search method." @default.
- W2953329907 created "2019-06-27" @default.
- W2953329907 creator A5055633714 @default.
- W2953329907 creator A5055819776 @default.
- W2953329907 creator A5057277609 @default.
- W2953329907 creator A5071367253 @default.
- W2953329907 creator A5072744508 @default.
- W2953329907 creator A5088394978 @default.
- W2953329907 date "2016-11-10" @default.
- W2953329907 modified "2023-10-14" @default.
- W2953329907 title "Policy Search with High-Dimensional Context Variables" @default.
- W2953329907 cites W1497915382 @default.
- W2953329907 cites W1506806321 @default.
- W2953329907 cites W1594871463 @default.
- W2953329907 cites W1685912164 @default.
- W2953329907 cites W2012587148 @default.
- W2953329907 cites W2045704273 @default.
- W2953329907 cites W2072128103 @default.
- W2953329907 cites W2091886411 @default.
- W2953329907 cites W2091956075 @default.
- W2953329907 cites W2117756735 @default.
- W2953329907 cites W2118550318 @default.
- W2953329907 cites W2123967136 @default.
- W2953329907 cites W2134332047 @default.
- W2953329907 cites W2138537392 @default.
- W2953329907 cites W2145831204 @default.
- W2953329907 cites W2148694408 @default.
- W2953329907 cites W2149860990 @default.
- W2953329907 cites W2185709919 @default.
- W2953329907 cites W2211399972 @default.
- W2953329907 cites W2296319761 @default.
- W2953329907 cites W2339666411 @default.
- W2953329907 cites W2951458352 @default.
- W2953329907 doi "https://doi.org/10.48550/arxiv.1611.03231" @default.
- W2953329907 hasPublicationYear "2016" @default.
- W2953329907 type Work @default.
- W2953329907 sameAs 2953329907 @default.
- W2953329907 citedByCount "0" @default.
- W2953329907 crossrefType "posted-content" @default.
- W2953329907 hasAuthorship W2953329907A5055633714 @default.
- W2953329907 hasAuthorship W2953329907A5055819776 @default.
- W2953329907 hasAuthorship W2953329907A5057277609 @default.
- W2953329907 hasAuthorship W2953329907A5071367253 @default.
- W2953329907 hasAuthorship W2953329907A5072744508 @default.
- W2953329907 hasAuthorship W2953329907A5088394978 @default.
- W2953329907 hasBestOaLocation W29533299071 @default.
- W2953329907 hasConcept C106301342 @default.
- W2953329907 hasConcept C111030470 @default.
- W2953329907 hasConcept C119857082 @default.
- W2953329907 hasConcept C121332964 @default.
- W2953329907 hasConcept C151730666 @default.
- W2953329907 hasConcept C154945302 @default.
- W2953329907 hasConcept C27438332 @default.
- W2953329907 hasConcept C2779343474 @default.
- W2953329907 hasConcept C41008148 @default.
- W2953329907 hasConcept C62520636 @default.
- W2953329907 hasConcept C70518039 @default.
- W2953329907 hasConcept C86803240 @default.
- W2953329907 hasConceptScore W2953329907C106301342 @default.
- W2953329907 hasConceptScore W2953329907C111030470 @default.
- W2953329907 hasConceptScore W2953329907C119857082 @default.
- W2953329907 hasConceptScore W2953329907C121332964 @default.
- W2953329907 hasConceptScore W2953329907C151730666 @default.
- W2953329907 hasConceptScore W2953329907C154945302 @default.
- W2953329907 hasConceptScore W2953329907C27438332 @default.
- W2953329907 hasConceptScore W2953329907C2779343474 @default.
- W2953329907 hasConceptScore W2953329907C41008148 @default.
- W2953329907 hasConceptScore W2953329907C62520636 @default.
- W2953329907 hasConceptScore W2953329907C70518039 @default.
- W2953329907 hasConceptScore W2953329907C86803240 @default.
- W2953329907 hasLocation W29533299071 @default.
- W2953329907 hasLocation W29533299072 @default.
- W2953329907 hasLocation W29533299073 @default.
- W2953329907 hasOpenAccess W2953329907 @default.
- W2953329907 hasPrimaryLocation W29533299071 @default.
- W2953329907 hasRelatedWork W1823429587 @default.
- W2953329907 hasRelatedWork W1995622179 @default.
- W2953329907 hasRelatedWork W2053420893 @default.
- W2953329907 hasRelatedWork W2097714737 @default.
- W2953329907 hasRelatedWork W2149386723 @default.
- W2953329907 hasRelatedWork W2162617165 @default.
- W2953329907 hasRelatedWork W2347335694 @default.
- W2953329907 hasRelatedWork W2611307339 @default.
- W2953329907 hasRelatedWork W3142002785 @default.
- W2953329907 hasRelatedWork W3153525586 @default.
- W2953329907 isParatext "false" @default.
- W2953329907 isRetracted "false" @default.
- W2953329907 magId "2953329907" @default.
- W2953329907 workType "article" @default.