FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1494114146> ?p ?o ?g. }

• W1494114146 endingPage "564" @default.
• W1494114146 startingPage "556" @default.
• W1494114146 abstract "Several researchers have proposed modeling temporally abstract actions in reinforcement learning by the combination of a policy and a termination condition, which we refer to as an option. Value functions over options and models of options can be learned using methods designed for semi-Markov decision processes (SMDPs). However, all these methods require an option to be executed to termination. In this paper we explore methods that learn about an option from small fragments of experience consistent with that option, even if the option itself is not executed. We call these methods intra-option learning methods because they learn from experience within an option. Intra-optionmethods are sometimes much more efficient than SMDP methods because they can use off-policy temporaldifference mechanisms to learn simultaneously about all the options consistent with an experience, not just the few that were actually executed. In this paper we present intra-option learning methods for learning value functions over options and for learning multi-time models of the consequences of options. We present computational examples in which these new methods learn much faster than SMDP methods and learn effectively when SMDP methods cannot learn at all. We also sketch a convergence proof for intraoption value learning." @default.
• W1494114146 created "2016-06-24" @default.
• W1494114146 creator A5004923102 @default.
• W1494114146 creator A5065366930 @default.
• W1494114146 creator A5065836447 @default.
• W1494114146 date "1998-07-24" @default.
• W1494114146 modified "2023-10-13" @default.
• W1494114146 title "Intra-Option Learning about Temporally Abstract Actions" @default.
• W1494114146 cites W1488730473 @default.
• W1494114146 cites W1507087299 @default.
• W1494114146 cites W1595483645 @default.
• W1494114146 cites W1600813180 @default.
• W1494114146 cites W16046748 @default.
• W1494114146 cites W1979071892 @default.
• W1494114146 cites W2016482167 @default.
• W1494114146 cites W2048226872 @default.
• W1494114146 cites W2056354534 @default.
• W1494114146 cites W2102000945 @default.
• W1494114146 cites W2114451917 @default.
• W1494114146 cites W2119567691 @default.
• W1494114146 cites W2121863487 @default.
• W1494114146 cites W2153947321 @default.
• W1494114146 cites W2156067405 @default.
• W1494114146 cites W2158548602 @default.
• W1494114146 cites W2160371091 @default.
• W1494114146 cites W2165131254 @default.
• W1494114146 cites W2343637401 @default.
• W1494114146 hasPublicationYear "1998" @default.
• W1494114146 type Work @default.
• W1494114146 sameAs 1494114146 @default.
• W1494114146 citedByCount "81" @default.
• W1494114146 countsByYear W14941141462012 @default.
• W1494114146 countsByYear W14941141462013 @default.
• W1494114146 countsByYear W14941141462014 @default.
• W1494114146 countsByYear W14941141462015 @default.
• W1494114146 countsByYear W14941141462016 @default.
• W1494114146 countsByYear W14941141462017 @default.
• W1494114146 countsByYear W14941141462018 @default.
• W1494114146 countsByYear W14941141462019 @default.
• W1494114146 countsByYear W14941141462020 @default.
• W1494114146 countsByYear W14941141462021 @default.
• W1494114146 crossrefType "proceedings-article" @default.
• W1494114146 hasAuthorship W1494114146A5004923102 @default.
• W1494114146 hasAuthorship W1494114146A5065366930 @default.
• W1494114146 hasAuthorship W1494114146A5065836447 @default.
• W1494114146 hasConcept C105795698 @default.
• W1494114146 hasConcept C106189395 @default.
• W1494114146 hasConcept C11413529 @default.
• W1494114146 hasConcept C119857082 @default.
• W1494114146 hasConcept C154945302 @default.
• W1494114146 hasConcept C159886148 @default.
• W1494114146 hasConcept C162324750 @default.
• W1494114146 hasConcept C188116033 @default.
• W1494114146 hasConcept C2776291640 @default.
• W1494114146 hasConcept C2777303404 @default.
• W1494114146 hasConcept C2779231336 @default.
• W1494114146 hasConcept C33923547 @default.
• W1494114146 hasConcept C41008148 @default.
• W1494114146 hasConcept C50522688 @default.
• W1494114146 hasConcept C97541855 @default.
• W1494114146 hasConceptScore W1494114146C105795698 @default.
• W1494114146 hasConceptScore W1494114146C106189395 @default.
• W1494114146 hasConceptScore W1494114146C11413529 @default.
• W1494114146 hasConceptScore W1494114146C119857082 @default.
• W1494114146 hasConceptScore W1494114146C154945302 @default.
• W1494114146 hasConceptScore W1494114146C159886148 @default.
• W1494114146 hasConceptScore W1494114146C162324750 @default.
• W1494114146 hasConceptScore W1494114146C188116033 @default.
• W1494114146 hasConceptScore W1494114146C2776291640 @default.
• W1494114146 hasConceptScore W1494114146C2777303404 @default.
• W1494114146 hasConceptScore W1494114146C2779231336 @default.
• W1494114146 hasConceptScore W1494114146C33923547 @default.
• W1494114146 hasConceptScore W1494114146C41008148 @default.
• W1494114146 hasConceptScore W1494114146C50522688 @default.
• W1494114146 hasConceptScore W1494114146C97541855 @default.
• W1494114146 hasLocation W14941141461 @default.
• W1494114146 hasOpenAccess W1494114146 @default.
• W1494114146 hasPrimaryLocation W14941141461 @default.
• W1494114146 hasRelatedWork W1488730473 @default.
• W1494114146 hasRelatedWork W1507087299 @default.
• W1494114146 hasRelatedWork W1515851193 @default.
• W1494114146 hasRelatedWork W1585861384 @default.
• W1494114146 hasRelatedWork W1592847719 @default.
• W1494114146 hasRelatedWork W2090170171 @default.
• W1494114146 hasRelatedWork W2107726111 @default.
• W1494114146 hasRelatedWork W2109910161 @default.
• W1494114146 hasRelatedWork W2114451917 @default.
• W1494114146 hasRelatedWork W2119567691 @default.
• W1494114146 hasRelatedWork W2121517924 @default.
• W1494114146 hasRelatedWork W2121863487 @default.
• W1494114146 hasRelatedWork W2139612737 @default.
• W1494114146 hasRelatedWork W2143435603 @default.
• W1494114146 hasRelatedWork W2145339207 @default.
• W1494114146 hasRelatedWork W2153947321 @default.
• W1494114146 hasRelatedWork W2158548602 @default.
• W1494114146 hasRelatedWork W2160371091 @default.
• W1494114146 hasRelatedWork W2335959470 @default.
• W1494114146 hasRelatedWork W3011120880 @default.

• next