FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3103256699> ?p ?o ?g. }

• W3103256699 endingPage "104" @default.
• W3103256699 startingPage "59" @default.
• W3103256699 abstract "This paper discusses a system that accelerates reinforcement learning by using transfer from related tasks. Without such transfer, even if two tasks are very similar at some abstract level, an extensive re-learning effort is required. The system achieves much of its power by transferring parts of previously learned solutions rather than a single complete solution. The system exploits strong features in the multi-dimensional function produced by reinforcement learning in solving a particular task. These features are stable and easy to recognize early in the learning process. They generate a partitioning of the state space and thus the function. The partition is represented as a graph. This is used to index and compose functions stored in a case base to form a close approximation to the solution of the new task. Experiments demonstrate that function composition often produces more than an order of magnitude increase in learning rate compared to a basic reinforcement learning algorithm." @default.
• W3103256699 created "2020-11-23" @default.
• W3103256699 creator A5008074314 @default.
• W3103256699 date "2002-02-01" @default.
• W3103256699 modified "2023-10-10" @default.
• W3103256699 title "Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks" @default.
• W3103256699 cites W111328409 @default.
• W3103256699 cites W1491843047 @default.
• W3103256699 cites W1498777242 @default.
• W3103256699 cites W1503397486 @default.
• W3103256699 cites W1515851193 @default.
• W3103256699 cites W1525507633 @default.
• W3103256699 cites W1547105496 @default.
• W3103256699 cites W1557415102 @default.
• W3103256699 cites W1557798492 @default.
• W3103256699 cites W1570690983 @default.
• W3103256699 cites W1583911959 @default.
• W3103256699 cites W1593437403 @default.
• W3103256699 cites W1597739853 @default.
• W3103256699 cites W1600813180 @default.
• W3103256699 cites W16046748 @default.
• W3103256699 cites W1631187438 @default.
• W3103256699 cites W1748123235 @default.
• W3103256699 cites W1979071892 @default.
• W3103256699 cites W1998100422 @default.
• W3103256699 cites W2004217976 @default.
• W3103256699 cites W2019553201 @default.
• W3103256699 cites W2026311529 @default.
• W3103256699 cites W2048226872 @default.
• W3103256699 cites W2080090262 @default.
• W3103256699 cites W2104095591 @default.
• W3103256699 cites W2108270708 @default.
• W3103256699 cites W2113913482 @default.
• W3103256699 cites W2114451917 @default.
• W3103256699 cites W2124175081 @default.
• W3103256699 cites W2132663727 @default.
• W3103256699 cites W2139762693 @default.
• W3103256699 cites W2159537329 @default.
• W3103256699 cites W2162837059 @default.
• W3103256699 cites W2165299353 @default.
• W3103256699 cites W2169528473 @default.
• W3103256699 cites W2172246523 @default.
• W3103256699 cites W22416704 @default.
• W3103256699 cites W2401825812 @default.
• W3103256699 cites W26561893 @default.
• W3103256699 cites W32403112 @default.
• W3103256699 cites W68612288 @default.
• W3103256699 cites W98997153 @default.
• W3103256699 doi "https://doi.org/10.1613/jair.904" @default.
• W3103256699 hasPublicationYear "2002" @default.
• W3103256699 type Work @default.
• W3103256699 sameAs 3103256699 @default.
• W3103256699 citedByCount "52" @default.
• W3103256699 countsByYear W31032566992012 @default.
• W3103256699 countsByYear W31032566992013 @default.
• W3103256699 countsByYear W31032566992014 @default.
• W3103256699 countsByYear W31032566992015 @default.
• W3103256699 countsByYear W31032566992016 @default.
• W3103256699 countsByYear W31032566992017 @default.
• W3103256699 countsByYear W31032566992018 @default.
• W3103256699 countsByYear W31032566992019 @default.
• W3103256699 countsByYear W31032566992020 @default.
• W3103256699 countsByYear W31032566992021 @default.
• W3103256699 countsByYear W31032566992022 @default.
• W3103256699 crossrefType "journal-article" @default.
• W3103256699 hasAuthorship W3103256699A5008074314 @default.
• W3103256699 hasBestOaLocation W31032566991 @default.
• W3103256699 hasConcept C105795698 @default.
• W3103256699 hasConcept C114614502 @default.
• W3103256699 hasConcept C119857082 @default.
• W3103256699 hasConcept C132525143 @default.
• W3103256699 hasConcept C134306372 @default.
• W3103256699 hasConcept C14036430 @default.
• W3103256699 hasConcept C150899416 @default.
• W3103256699 hasConcept C154945302 @default.
• W3103256699 hasConcept C15744967 @default.
• W3103256699 hasConcept C162324750 @default.
• W3103256699 hasConcept C165696696 @default.
• W3103256699 hasConcept C187736073 @default.
• W3103256699 hasConcept C2780451532 @default.
• W3103256699 hasConcept C33923547 @default.
• W3103256699 hasConcept C38652104 @default.
• W3103256699 hasConcept C41008148 @default.
• W3103256699 hasConcept C42058472 @default.
• W3103256699 hasConcept C42812 @default.
• W3103256699 hasConcept C67203356 @default.
• W3103256699 hasConcept C72434380 @default.
• W3103256699 hasConcept C77805123 @default.
• W3103256699 hasConcept C78458016 @default.
• W3103256699 hasConcept C80444323 @default.
• W3103256699 hasConcept C86803240 @default.
• W3103256699 hasConcept C97541855 @default.
• W3103256699 hasConceptScore W3103256699C105795698 @default.
• W3103256699 hasConceptScore W3103256699C114614502 @default.
• W3103256699 hasConceptScore W3103256699C119857082 @default.
• W3103256699 hasConceptScore W3103256699C132525143 @default.
• W3103256699 hasConceptScore W3103256699C134306372 @default.
• W3103256699 hasConceptScore W3103256699C14036430 @default.

• next