Matches in SemOpenAlex for { <https://semopenalex.org/work/W1634050171> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W1634050171 endingPage "446" @default.
- W1634050171 startingPage "439" @default.
- W1634050171 abstract "In this paper we introduce a budgeted knowledge transfer algorithm for non-homogeneous reinforcement learning agents. Here the source and the target agents are completely identical except in their state representations. The algorithm uses functional space (Q-value space) as the transfer-learning media. In this method, the target agent’s functional points (Q-values) are estimated in an automatically selected lower-dimension subspace in order to accelerate knowledge transfer. The target agent searches that subspace using an exploration policy and selects actions accordingly during the period of its knowledge transfer in order to facilitate gaining an appropriate estimate of its Q-table. We show both analytically and empirically that this method decreases the required learning budget for the target agent." @default.
- W1634050171 created "2016-06-24" @default.
- W1634050171 creator A5026311412 @default.
- W1634050171 creator A5040208292 @default.
- W1634050171 creator A5072135442 @default.
- W1634050171 date "2012-01-01" @default.
- W1634050171 modified "2023-10-16" @default.
- W1634050171 title "Budgeted Knowledge Transfer for State-Wise Heterogeneous RL Agents" @default.
- W1634050171 cites W2110292307 @default.
- W1634050171 cites W2154328025 @default.
- W1634050171 cites W2169743339 @default.
- W1634050171 doi "https://doi.org/10.1007/978-3-642-34475-6_53" @default.
- W1634050171 hasPublicationYear "2012" @default.
- W1634050171 type Work @default.
- W1634050171 sameAs 1634050171 @default.
- W1634050171 citedByCount "0" @default.
- W1634050171 crossrefType "book-chapter" @default.
- W1634050171 hasAuthorship W1634050171A5026311412 @default.
- W1634050171 hasAuthorship W1634050171A5040208292 @default.
- W1634050171 hasAuthorship W1634050171A5072135442 @default.
- W1634050171 hasBestOaLocation W16340501712 @default.
- W1634050171 hasConcept C105795698 @default.
- W1634050171 hasConcept C111919701 @default.
- W1634050171 hasConcept C114614502 @default.
- W1634050171 hasConcept C126255220 @default.
- W1634050171 hasConcept C150899416 @default.
- W1634050171 hasConcept C154945302 @default.
- W1634050171 hasConcept C173608175 @default.
- W1634050171 hasConcept C202444582 @default.
- W1634050171 hasConcept C2776175482 @default.
- W1634050171 hasConcept C2776960227 @default.
- W1634050171 hasConcept C2778572836 @default.
- W1634050171 hasConcept C32834561 @default.
- W1634050171 hasConcept C33676613 @default.
- W1634050171 hasConcept C33923547 @default.
- W1634050171 hasConcept C41008148 @default.
- W1634050171 hasConcept C56739046 @default.
- W1634050171 hasConcept C66882249 @default.
- W1634050171 hasConcept C72434380 @default.
- W1634050171 hasConcept C97541855 @default.
- W1634050171 hasConceptScore W1634050171C105795698 @default.
- W1634050171 hasConceptScore W1634050171C111919701 @default.
- W1634050171 hasConceptScore W1634050171C114614502 @default.
- W1634050171 hasConceptScore W1634050171C126255220 @default.
- W1634050171 hasConceptScore W1634050171C150899416 @default.
- W1634050171 hasConceptScore W1634050171C154945302 @default.
- W1634050171 hasConceptScore W1634050171C173608175 @default.
- W1634050171 hasConceptScore W1634050171C202444582 @default.
- W1634050171 hasConceptScore W1634050171C2776175482 @default.
- W1634050171 hasConceptScore W1634050171C2776960227 @default.
- W1634050171 hasConceptScore W1634050171C2778572836 @default.
- W1634050171 hasConceptScore W1634050171C32834561 @default.
- W1634050171 hasConceptScore W1634050171C33676613 @default.
- W1634050171 hasConceptScore W1634050171C33923547 @default.
- W1634050171 hasConceptScore W1634050171C41008148 @default.
- W1634050171 hasConceptScore W1634050171C56739046 @default.
- W1634050171 hasConceptScore W1634050171C66882249 @default.
- W1634050171 hasConceptScore W1634050171C72434380 @default.
- W1634050171 hasConceptScore W1634050171C97541855 @default.
- W1634050171 hasLocation W16340501711 @default.
- W1634050171 hasLocation W16340501712 @default.
- W1634050171 hasOpenAccess W1634050171 @default.
- W1634050171 hasPrimaryLocation W16340501711 @default.
- W1634050171 hasRelatedWork W1634050171 @default.
- W1634050171 hasRelatedWork W197857547 @default.
- W1634050171 hasRelatedWork W1997664188 @default.
- W1634050171 hasRelatedWork W2158766333 @default.
- W1634050171 hasRelatedWork W2352771842 @default.
- W1634050171 hasRelatedWork W2414642799 @default.
- W1634050171 hasRelatedWork W2899403804 @default.
- W1634050171 hasRelatedWork W3170446423 @default.
- W1634050171 hasRelatedWork W4225907548 @default.
- W1634050171 hasRelatedWork W4308233397 @default.
- W1634050171 isParatext "false" @default.
- W1634050171 isRetracted "false" @default.
- W1634050171 magId "1634050171" @default.
- W1634050171 workType "book-chapter" @default.