Matches in SemOpenAlex for { <https://semopenalex.org/work/W2012036715> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2012036715 endingPage "339" @default.
- W2012036715 startingPage "323" @default.
- W2012036715 abstract "Although building sophisticated learning agents that operate in complex environments will require learning to perform multiple tasks, most applications of reinforcement learning have focused on single tasks. In this paper I consider a class of sequential decision tasks (SDTs), called composite sequential decision tasks, formed by temporally concatenating a number of elemental sequential decision tasks. Elemental SDTs cannot be decomposed into simpler SDTs. I consider a learning agent that has to learn to solve a set of elemental and composite SDTs. I assume that the structure of the composite tasks is unknown to the learning agent. The straightforward application of reinforcement learning to multiple tasks requires learning the tasks separately, which can waste computational resources, both memory and time. I present a new learning algorithm and a modular architecture that learns the decomposition of composite SDTs, and achieves transfer of learning by sharing the solutions of elemental SDTs across multiple composite SDTs. The solution of a composite SDT is constructed by computationally inexpensive modifications of the solutions of its constituent elemental SDTs. I provide a proof of one aspect of the learning algorithm." @default.
- W2012036715 created "2016-06-24" @default.
- W2012036715 creator A5065366930 @default.
- W2012036715 date "1992-05-01" @default.
- W2012036715 modified "2023-09-25" @default.
- W2012036715 title "Transfer of learning by composing solutions of elemental sequential tasks" @default.
- W2012036715 cites W1500024457 @default.
- W2012036715 cites W2150884987 @default.
- W2012036715 cites W2624516165 @default.
- W2012036715 doi "https://doi.org/10.1007/bf00992700" @default.
- W2012036715 hasPublicationYear "1992" @default.
- W2012036715 type Work @default.
- W2012036715 sameAs 2012036715 @default.
- W2012036715 citedByCount "240" @default.
- W2012036715 countsByYear W20120367152012 @default.
- W2012036715 countsByYear W20120367152013 @default.
- W2012036715 countsByYear W20120367152014 @default.
- W2012036715 countsByYear W20120367152015 @default.
- W2012036715 countsByYear W20120367152017 @default.
- W2012036715 countsByYear W20120367152018 @default.
- W2012036715 countsByYear W20120367152019 @default.
- W2012036715 countsByYear W20120367152020 @default.
- W2012036715 countsByYear W20120367152021 @default.
- W2012036715 countsByYear W20120367152022 @default.
- W2012036715 countsByYear W20120367152023 @default.
- W2012036715 crossrefType "journal-article" @default.
- W2012036715 hasAuthorship W2012036715A5065366930 @default.
- W2012036715 hasBestOaLocation W20120367151 @default.
- W2012036715 hasConcept C101468663 @default.
- W2012036715 hasConcept C104779481 @default.
- W2012036715 hasConcept C11413529 @default.
- W2012036715 hasConcept C119857082 @default.
- W2012036715 hasConcept C150899416 @default.
- W2012036715 hasConcept C154945302 @default.
- W2012036715 hasConcept C199360897 @default.
- W2012036715 hasConcept C41008148 @default.
- W2012036715 hasConcept C97541855 @default.
- W2012036715 hasConceptScore W2012036715C101468663 @default.
- W2012036715 hasConceptScore W2012036715C104779481 @default.
- W2012036715 hasConceptScore W2012036715C11413529 @default.
- W2012036715 hasConceptScore W2012036715C119857082 @default.
- W2012036715 hasConceptScore W2012036715C150899416 @default.
- W2012036715 hasConceptScore W2012036715C154945302 @default.
- W2012036715 hasConceptScore W2012036715C199360897 @default.
- W2012036715 hasConceptScore W2012036715C41008148 @default.
- W2012036715 hasConceptScore W2012036715C97541855 @default.
- W2012036715 hasIssue "3-4" @default.
- W2012036715 hasLocation W20120367151 @default.
- W2012036715 hasOpenAccess W2012036715 @default.
- W2012036715 hasPrimaryLocation W20120367151 @default.
- W2012036715 hasRelatedWork W2960456850 @default.
- W2012036715 hasRelatedWork W3022038857 @default.
- W2012036715 hasRelatedWork W3209094908 @default.
- W2012036715 hasRelatedWork W4213299466 @default.
- W2012036715 hasRelatedWork W4281382123 @default.
- W2012036715 hasRelatedWork W4281645081 @default.
- W2012036715 hasRelatedWork W4308262314 @default.
- W2012036715 hasRelatedWork W4318834068 @default.
- W2012036715 hasRelatedWork W4318957922 @default.
- W2012036715 hasRelatedWork W4319083788 @default.
- W2012036715 hasVolume "8" @default.
- W2012036715 isParatext "false" @default.
- W2012036715 isRetracted "false" @default.
- W2012036715 magId "2012036715" @default.
- W2012036715 workType "article" @default.