Matches in SemOpenAlex for { <https://semopenalex.org/work/W2519270595> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2519270595 endingPage "2195" @default.
- W2519270595 startingPage "2187" @default.
- W2519270595 abstract "In this paper we introduce a multi-step linear Dyna-style planning algorithm. The key element of the multi-step linear Dyna is a multi-step linear model that enables multi-step projection of a sampled feature and multi-step planning based on the simulated multi-step transition experience. We propose two multi-step linear models. The first iterates the one-step linear model, but is generally computationally complex. The second interpolates between the one-step model and the infinite-step model (which turns out to be the LSTD solution), and can be learned efficiently online. Policy evaluation on Boyan Chain shows that multi-step linear Dyna learns a policy faster than single-step linear Dyna, and generally learns faster as the number of projection steps increases. Results on Mountain-car show that multi-step linear Dyna leads to much better online performance than single-step linear Dyna and model-free algorithms; however, the performance of multi-step linear Dyna does not always improve as the number of projection steps increases. Our results also suggest that previous attempts on extending LSTD for online control were unsuccessful because LSTD looks infinite steps into the future, and suffers from the model errors in non-stationary (control) environments." @default.
- W2519270595 created "2016-09-23" @default.
- W2519270595 creator A5038163398 @default.
- W2519270595 creator A5038852619 @default.
- W2519270595 creator A5050876115 @default.
- W2519270595 date "2009-12-07" @default.
- W2519270595 modified "2023-10-18" @default.
- W2519270595 title "Multi-step linear Dyna-style planning" @default.
- W2519270595 cites W1491843047 @default.
- W2519270595 cites W1515851193 @default.
- W2519270595 cites W1518539242 @default.
- W2519270595 cites W1594216983 @default.
- W2519270595 cites W1597303641 @default.
- W2519270595 cites W1758031947 @default.
- W2519270595 cites W2072931156 @default.
- W2519270595 cites W2121863487 @default.
- W2519270595 cites W2130005627 @default.
- W2519270595 cites W2134882417 @default.
- W2519270595 cites W2139418546 @default.
- W2519270595 cites W2150923691 @default.
- W2519270595 cites W2172968643 @default.
- W2519270595 hasPublicationYear "2009" @default.
- W2519270595 type Work @default.
- W2519270595 sameAs 2519270595 @default.
- W2519270595 citedByCount "3" @default.
- W2519270595 countsByYear W25192705952015 @default.
- W2519270595 countsByYear W25192705952021 @default.
- W2519270595 crossrefType "proceedings-article" @default.
- W2519270595 hasAuthorship W2519270595A5038163398 @default.
- W2519270595 hasAuthorship W2519270595A5038852619 @default.
- W2519270595 hasAuthorship W2519270595A5050876115 @default.
- W2519270595 hasConcept C11413529 @default.
- W2519270595 hasConcept C119857082 @default.
- W2519270595 hasConcept C134306372 @default.
- W2519270595 hasConcept C138885662 @default.
- W2519270595 hasConcept C140479938 @default.
- W2519270595 hasConcept C163175372 @default.
- W2519270595 hasConcept C2776401178 @default.
- W2519270595 hasConcept C33923547 @default.
- W2519270595 hasConcept C41008148 @default.
- W2519270595 hasConcept C41895202 @default.
- W2519270595 hasConcept C57493831 @default.
- W2519270595 hasConceptScore W2519270595C11413529 @default.
- W2519270595 hasConceptScore W2519270595C119857082 @default.
- W2519270595 hasConceptScore W2519270595C134306372 @default.
- W2519270595 hasConceptScore W2519270595C138885662 @default.
- W2519270595 hasConceptScore W2519270595C140479938 @default.
- W2519270595 hasConceptScore W2519270595C163175372 @default.
- W2519270595 hasConceptScore W2519270595C2776401178 @default.
- W2519270595 hasConceptScore W2519270595C33923547 @default.
- W2519270595 hasConceptScore W2519270595C41008148 @default.
- W2519270595 hasConceptScore W2519270595C41895202 @default.
- W2519270595 hasConceptScore W2519270595C57493831 @default.
- W2519270595 hasLocation W25192705951 @default.
- W2519270595 hasOpenAccess W2519270595 @default.
- W2519270595 hasPrimaryLocation W25192705951 @default.
- W2519270595 hasRelatedWork W1541322738 @default.
- W2519270595 hasRelatedWork W2006402699 @default.
- W2519270595 hasRelatedWork W2068122595 @default.
- W2519270595 hasRelatedWork W2096801802 @default.
- W2519270595 hasRelatedWork W2108384499 @default.
- W2519270595 hasRelatedWork W2291318941 @default.
- W2519270595 hasRelatedWork W2528203928 @default.
- W2519270595 hasRelatedWork W2592490816 @default.
- W2519270595 hasRelatedWork W2612359487 @default.
- W2519270595 hasRelatedWork W2766248009 @default.
- W2519270595 hasRelatedWork W2771208017 @default.
- W2519270595 hasRelatedWork W2912668400 @default.
- W2519270595 hasRelatedWork W2922289374 @default.
- W2519270595 hasRelatedWork W2948566442 @default.
- W2519270595 hasRelatedWork W2963912340 @default.
- W2519270595 hasRelatedWork W2990675203 @default.
- W2519270595 hasRelatedWork W3112996104 @default.
- W2519270595 hasRelatedWork W3121329062 @default.
- W2519270595 hasRelatedWork W3180361647 @default.
- W2519270595 hasRelatedWork W866641798 @default.
- W2519270595 isParatext "false" @default.
- W2519270595 isRetracted "false" @default.
- W2519270595 magId "2519270595" @default.
- W2519270595 workType "article" @default.