Matches in SemOpenAlex for { <https://semopenalex.org/work/W137325057> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W137325057 endingPage "1218" @default.
- W137325057 startingPage "1212" @default.
- W137325057 abstract "In this paper we consider the problem of finding a good policy given some batch data.We propose a new approach, LAM-API, that first builds a so-called linear action model (LAM) from the data and then uses the learned model and the collected data in approximate policy iteration (API) to find a good policy.A natural choice for the policy evaluation step in this algorithm is to use least-squares temporal difference (LSTD) learning algorithm.Empirical results on three benchmark problems show that this particular instance of LAM-API performs competitively as compared with LSPI, both from the point of view of data and computational efficiency." @default.
- W137325057 created "2016-06-24" @default.
- W137325057 creator A5050876115 @default.
- W137325057 creator A5069856068 @default.
- W137325057 date "2021-09-20" @default.
- W137325057 modified "2023-10-05" @default.
- W137325057 title "Approximate Policy Iteration with Linear Action Models" @default.
- W137325057 cites W1515851193 @default.
- W137325057 cites W1540821927 @default.
- W137325057 cites W1549543673 @default.
- W137325057 cites W1576452626 @default.
- W137325057 cites W1758031947 @default.
- W137325057 cites W1876478031 @default.
- W137325057 cites W2028145673 @default.
- W137325057 cites W2072931156 @default.
- W137325057 cites W2073384958 @default.
- W137325057 cites W2075268401 @default.
- W137325057 cites W2121863487 @default.
- W137325057 cites W2123979492 @default.
- W137325057 cites W2130005627 @default.
- W137325057 cites W2132351269 @default.
- W137325057 cites W2912453235 @default.
- W137325057 cites W359568995 @default.
- W137325057 doi "https://doi.org/10.1609/aaai.v26i1.8319" @default.
- W137325057 hasPublicationYear "2021" @default.
- W137325057 type Work @default.
- W137325057 sameAs 137325057 @default.
- W137325057 citedByCount "7" @default.
- W137325057 countsByYear W1373250572014 @default.
- W137325057 countsByYear W1373250572016 @default.
- W137325057 countsByYear W1373250572017 @default.
- W137325057 countsByYear W1373250572018 @default.
- W137325057 countsByYear W1373250572019 @default.
- W137325057 countsByYear W1373250572023 @default.
- W137325057 crossrefType "journal-article" @default.
- W137325057 hasAuthorship W137325057A5050876115 @default.
- W137325057 hasAuthorship W137325057A5069856068 @default.
- W137325057 hasBestOaLocation W1373250571 @default.
- W137325057 hasConcept C121332964 @default.
- W137325057 hasConcept C126255220 @default.
- W137325057 hasConcept C13280743 @default.
- W137325057 hasConcept C154945302 @default.
- W137325057 hasConcept C185798385 @default.
- W137325057 hasConcept C196340769 @default.
- W137325057 hasConcept C205649164 @default.
- W137325057 hasConcept C2524010 @default.
- W137325057 hasConcept C2780791683 @default.
- W137325057 hasConcept C28719098 @default.
- W137325057 hasConcept C33923547 @default.
- W137325057 hasConcept C41008148 @default.
- W137325057 hasConcept C62520636 @default.
- W137325057 hasConcept C97541855 @default.
- W137325057 hasConceptScore W137325057C121332964 @default.
- W137325057 hasConceptScore W137325057C126255220 @default.
- W137325057 hasConceptScore W137325057C13280743 @default.
- W137325057 hasConceptScore W137325057C154945302 @default.
- W137325057 hasConceptScore W137325057C185798385 @default.
- W137325057 hasConceptScore W137325057C196340769 @default.
- W137325057 hasConceptScore W137325057C205649164 @default.
- W137325057 hasConceptScore W137325057C2524010 @default.
- W137325057 hasConceptScore W137325057C2780791683 @default.
- W137325057 hasConceptScore W137325057C28719098 @default.
- W137325057 hasConceptScore W137325057C33923547 @default.
- W137325057 hasConceptScore W137325057C41008148 @default.
- W137325057 hasConceptScore W137325057C62520636 @default.
- W137325057 hasConceptScore W137325057C97541855 @default.
- W137325057 hasIssue "1" @default.
- W137325057 hasLocation W1373250571 @default.
- W137325057 hasLocation W1373250572 @default.
- W137325057 hasOpenAccess W137325057 @default.
- W137325057 hasPrimaryLocation W1373250571 @default.
- W137325057 hasRelatedWork W112744582 @default.
- W137325057 hasRelatedWork W1485630101 @default.
- W137325057 hasRelatedWork W1490303524 @default.
- W137325057 hasRelatedWork W1677601786 @default.
- W137325057 hasRelatedWork W2030059621 @default.
- W137325057 hasRelatedWork W2498017833 @default.
- W137325057 hasRelatedWork W3033750096 @default.
- W137325057 hasRelatedWork W3081841992 @default.
- W137325057 hasRelatedWork W3084863322 @default.
- W137325057 hasRelatedWork W3107474891 @default.
- W137325057 hasVolume "26" @default.
- W137325057 isParatext "false" @default.
- W137325057 isRetracted "false" @default.
- W137325057 magId "137325057" @default.
- W137325057 workType "article" @default.