Matches in SemOpenAlex for { <https://semopenalex.org/work/W4237359839> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4237359839 endingPage "217" @default.
- W4237359839 startingPage "190" @default.
- W4237359839 abstract "This chapter introduces an approach for reinforcement learning based on a relational representation that: (i) can be applied over large search spaces, (ii) can incorporate domain knowledge, and (iii) can use previously learned policies on different, but similar, problems. The underlying idea is to represent states as sets of first order relations, actions in terms of those relations, and to learn policies over such generalized representation. It is shown how this representation can produce powerful abstractions and that policies learned over this generalized representation can be directly applied, without any further learning, to other problems that can be characterized by the same set of relations. To accelerate the learning process, we present an extension where traces of the tasks to be learned are provided by the user. These traces are used to select only a small subset of possible actions increasing the convergence of the learning algorithms. The effectiveness of the approach is tested on a flight simulator and on a mobile robot." @default.
- W4237359839 created "2022-05-12" @default.
- W4237359839 creator A5031990673 @default.
- W4237359839 creator A5059686966 @default.
- W4237359839 date "2012-01-01" @default.
- W4237359839 modified "2023-09-25" @default.
- W4237359839 title "Relational Representations and Traces for Efficient Reinforcement Learning" @default.
- W4237359839 cites W1490954610 @default.
- W4237359839 cites W1511887321 @default.
- W4237359839 cites W1572710235 @default.
- W4237359839 cites W1574001572 @default.
- W4237359839 cites W1585529040 @default.
- W4237359839 cites W1678356000 @default.
- W4237359839 cites W1977970897 @default.
- W4237359839 cites W1987187457 @default.
- W4237359839 cites W2033072307 @default.
- W4237359839 cites W2086472796 @default.
- W4237359839 cites W2088853743 @default.
- W4237359839 cites W2109910161 @default.
- W4237359839 cites W2119242513 @default.
- W4237359839 cites W2121517924 @default.
- W4237359839 cites W2125922627 @default.
- W4237359839 cites W2131859354 @default.
- W4237359839 cites W2168359464 @default.
- W4237359839 cites W2334782222 @default.
- W4237359839 cites W3020831056 @default.
- W4237359839 cites W4206370914 @default.
- W4237359839 doi "https://doi.org/10.4018/978-1-60960-165-2.ch009" @default.
- W4237359839 hasPublicationYear "2012" @default.
- W4237359839 type Work @default.
- W4237359839 citedByCount "0" @default.
- W4237359839 crossrefType "book-chapter" @default.
- W4237359839 hasAuthorship W4237359839A5031990673 @default.
- W4237359839 hasAuthorship W4237359839A5059686966 @default.
- W4237359839 hasConcept C134306372 @default.
- W4237359839 hasConcept C154945302 @default.
- W4237359839 hasConcept C162324750 @default.
- W4237359839 hasConcept C177264268 @default.
- W4237359839 hasConcept C17744445 @default.
- W4237359839 hasConcept C177877439 @default.
- W4237359839 hasConcept C199360897 @default.
- W4237359839 hasConcept C199539241 @default.
- W4237359839 hasConcept C23123220 @default.
- W4237359839 hasConcept C2776359362 @default.
- W4237359839 hasConcept C2777303404 @default.
- W4237359839 hasConcept C2778029271 @default.
- W4237359839 hasConcept C33923547 @default.
- W4237359839 hasConcept C36503486 @default.
- W4237359839 hasConcept C41008148 @default.
- W4237359839 hasConcept C50522688 @default.
- W4237359839 hasConcept C5655090 @default.
- W4237359839 hasConcept C80444323 @default.
- W4237359839 hasConcept C94625758 @default.
- W4237359839 hasConcept C97541855 @default.
- W4237359839 hasConcept C98045186 @default.
- W4237359839 hasConceptScore W4237359839C134306372 @default.
- W4237359839 hasConceptScore W4237359839C154945302 @default.
- W4237359839 hasConceptScore W4237359839C162324750 @default.
- W4237359839 hasConceptScore W4237359839C177264268 @default.
- W4237359839 hasConceptScore W4237359839C17744445 @default.
- W4237359839 hasConceptScore W4237359839C177877439 @default.
- W4237359839 hasConceptScore W4237359839C199360897 @default.
- W4237359839 hasConceptScore W4237359839C199539241 @default.
- W4237359839 hasConceptScore W4237359839C23123220 @default.
- W4237359839 hasConceptScore W4237359839C2776359362 @default.
- W4237359839 hasConceptScore W4237359839C2777303404 @default.
- W4237359839 hasConceptScore W4237359839C2778029271 @default.
- W4237359839 hasConceptScore W4237359839C33923547 @default.
- W4237359839 hasConceptScore W4237359839C36503486 @default.
- W4237359839 hasConceptScore W4237359839C41008148 @default.
- W4237359839 hasConceptScore W4237359839C50522688 @default.
- W4237359839 hasConceptScore W4237359839C5655090 @default.
- W4237359839 hasConceptScore W4237359839C80444323 @default.
- W4237359839 hasConceptScore W4237359839C94625758 @default.
- W4237359839 hasConceptScore W4237359839C97541855 @default.
- W4237359839 hasConceptScore W4237359839C98045186 @default.
- W4237359839 hasLocation W42373598391 @default.
- W4237359839 hasOpenAccess W4237359839 @default.
- W4237359839 hasPrimaryLocation W42373598391 @default.
- W4237359839 hasRelatedWork W14796669 @default.
- W4237359839 hasRelatedWork W16369016 @default.
- W4237359839 hasRelatedWork W18922318 @default.
- W4237359839 hasRelatedWork W21168118 @default.
- W4237359839 hasRelatedWork W2990258 @default.
- W4237359839 hasRelatedWork W3476873 @default.
- W4237359839 hasRelatedWork W868042 @default.
- W4237359839 hasRelatedWork W8692371 @default.
- W4237359839 hasRelatedWork W8794964 @default.
- W4237359839 hasRelatedWork W3786644 @default.
- W4237359839 isParatext "false" @default.
- W4237359839 isRetracted "false" @default.
- W4237359839 workType "book-chapter" @default.