Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890260778> ?p ?o ?g. }
- W2890260778 endingPage "6189" @default.
- W2890260778 startingPage "6179" @default.
- W2890260778 abstract "We consider the problem of transferring value functions in reinforcement learning. We propose an approach that uses the given source tasks to learn a prior distribution over optimal value functions and provide an efficient variational approximation of the corresponding posterior in a new target task. We show our approach to be general, in the sense that it can be combined with complex parametric function approximators and distribution models, while providing two practical algorithms based on Gaussians and Gaussian mixtures. We theoretically analyze them by deriving a finite-sample analysis and provide a comprehensive empirical evaluation in four different domains." @default.
- W2890260778 created "2018-09-27" @default.
- W2890260778 creator A5009259116 @default.
- W2890260778 creator A5015216456 @default.
- W2890260778 creator A5017130830 @default.
- W2890260778 date "2018-01-01" @default.
- W2890260778 modified "2023-09-24" @default.
- W2890260778 title "Transfer of Value Functions via Variational Methods" @default.
- W2890260778 cites W1492014007 @default.
- W2890260778 cites W158722652 @default.
- W2890260778 cites W1646707810 @default.
- W2890260778 cites W2004030284 @default.
- W2890260778 cites W2012392077 @default.
- W2890260778 cites W2031727428 @default.
- W2890260778 cites W2033178790 @default.
- W2890260778 cites W2049934117 @default.
- W2890260778 cites W2079247031 @default.
- W2890260778 cites W2097381042 @default.
- W2890260778 cites W2110292307 @default.
- W2890260778 cites W2119567691 @default.
- W2890260778 cites W2145339207 @default.
- W2890260778 cites W2155968351 @default.
- W2890260778 cites W2163288162 @default.
- W2890260778 cites W2166851633 @default.
- W2890260778 cites W2169743339 @default.
- W2890260778 cites W2257979135 @default.
- W2890260778 cites W2604763608 @default.
- W2890260778 cites W2962717849 @default.
- W2890260778 cites W2962928691 @default.
- W2890260778 cites W2963169817 @default.
- W2890260778 cites W2964015990 @default.
- W2890260778 cites W2964022604 @default.
- W2890260778 cites W2964161785 @default.
- W2890260778 hasPublicationYear "2018" @default.
- W2890260778 type Work @default.
- W2890260778 sameAs 2890260778 @default.
- W2890260778 citedByCount "10" @default.
- W2890260778 countsByYear W28902607782019 @default.
- W2890260778 countsByYear W28902607782020 @default.
- W2890260778 countsByYear W28902607782021 @default.
- W2890260778 crossrefType "proceedings-article" @default.
- W2890260778 hasAuthorship W2890260778A5009259116 @default.
- W2890260778 hasAuthorship W2890260778A5015216456 @default.
- W2890260778 hasAuthorship W2890260778A5017130830 @default.
- W2890260778 hasConcept C105795698 @default.
- W2890260778 hasConcept C11413529 @default.
- W2890260778 hasConcept C117251300 @default.
- W2890260778 hasConcept C119857082 @default.
- W2890260778 hasConcept C121332964 @default.
- W2890260778 hasConcept C126255220 @default.
- W2890260778 hasConcept C14036430 @default.
- W2890260778 hasConcept C14646407 @default.
- W2890260778 hasConcept C154945302 @default.
- W2890260778 hasConcept C162324750 @default.
- W2890260778 hasConcept C163716315 @default.
- W2890260778 hasConcept C185592680 @default.
- W2890260778 hasConcept C187736073 @default.
- W2890260778 hasConcept C198531522 @default.
- W2890260778 hasConcept C2776291640 @default.
- W2890260778 hasConcept C2780451532 @default.
- W2890260778 hasConcept C28826006 @default.
- W2890260778 hasConcept C33923547 @default.
- W2890260778 hasConcept C41008148 @default.
- W2890260778 hasConcept C43617362 @default.
- W2890260778 hasConcept C50644808 @default.
- W2890260778 hasConcept C62520636 @default.
- W2890260778 hasConcept C78458016 @default.
- W2890260778 hasConcept C86803240 @default.
- W2890260778 hasConcept C91873725 @default.
- W2890260778 hasConcept C97541855 @default.
- W2890260778 hasConceptScore W2890260778C105795698 @default.
- W2890260778 hasConceptScore W2890260778C11413529 @default.
- W2890260778 hasConceptScore W2890260778C117251300 @default.
- W2890260778 hasConceptScore W2890260778C119857082 @default.
- W2890260778 hasConceptScore W2890260778C121332964 @default.
- W2890260778 hasConceptScore W2890260778C126255220 @default.
- W2890260778 hasConceptScore W2890260778C14036430 @default.
- W2890260778 hasConceptScore W2890260778C14646407 @default.
- W2890260778 hasConceptScore W2890260778C154945302 @default.
- W2890260778 hasConceptScore W2890260778C162324750 @default.
- W2890260778 hasConceptScore W2890260778C163716315 @default.
- W2890260778 hasConceptScore W2890260778C185592680 @default.
- W2890260778 hasConceptScore W2890260778C187736073 @default.
- W2890260778 hasConceptScore W2890260778C198531522 @default.
- W2890260778 hasConceptScore W2890260778C2776291640 @default.
- W2890260778 hasConceptScore W2890260778C2780451532 @default.
- W2890260778 hasConceptScore W2890260778C28826006 @default.
- W2890260778 hasConceptScore W2890260778C33923547 @default.
- W2890260778 hasConceptScore W2890260778C41008148 @default.
- W2890260778 hasConceptScore W2890260778C43617362 @default.
- W2890260778 hasConceptScore W2890260778C50644808 @default.
- W2890260778 hasConceptScore W2890260778C62520636 @default.
- W2890260778 hasConceptScore W2890260778C78458016 @default.
- W2890260778 hasConceptScore W2890260778C86803240 @default.
- W2890260778 hasConceptScore W2890260778C91873725 @default.
- W2890260778 hasConceptScore W2890260778C97541855 @default.
- W2890260778 hasLocation W28902607781 @default.
- W2890260778 hasOpenAccess W2890260778 @default.