Matches in SemOpenAlex for { <https://semopenalex.org/work/W2089938274> ?p ?o ?g. }
- W2089938274 abstract "In the reinforcement leaning task, the off-policy algorithms which approximately evaluate the values of states faced with the problem of high evaluation error and were sensitive to the distribution of behavior policy. In order to solve these problems, the basis function optimization method under the off-policy scenario was proposed. The algorithm set the Bellman error of the target policy which was computed with off-policy prediction algorithms as the objective function, then adjust the placement and shape of the basis functions in cooperate with the method of cross-entropy optimization. The experimental results on the grid world show that the algorithm effectively reduced the evaluation error and improved the approximation. Additionally, the algorithm could be easily extended to the problems of large state spaces." @default.
- W2089938274 created "2016-06-24" @default.
- W2089938274 creator A5026708634 @default.
- W2089938274 creator A5034525395 @default.
- W2089938274 date "2014-08-01" @default.
- W2089938274 modified "2023-09-25" @default.
- W2089938274 title "Research of an off-policy BF optimization aloorithm based on cross-entroropy method" @default.
- W2089938274 cites W1600046456 @default.
- W2089938274 cites W1626155273 @default.
- W2089938274 cites W1998172110 @default.
- W2089938274 cites W2108051346 @default.
- W2089938274 cites W2125510930 @default.
- W2089938274 cites W2153267861 @default.
- W2089938274 doi "https://doi.org/10.1109/wac.2014.6936177" @default.
- W2089938274 hasPublicationYear "2014" @default.
- W2089938274 type Work @default.
- W2089938274 sameAs 2089938274 @default.
- W2089938274 citedByCount "0" @default.
- W2089938274 crossrefType "proceedings-article" @default.
- W2089938274 hasAuthorship W2089938274A5026708634 @default.
- W2089938274 hasAuthorship W2089938274A5034525395 @default.
- W2089938274 hasConcept C106301342 @default.
- W2089938274 hasConcept C11413529 @default.
- W2089938274 hasConcept C121332964 @default.
- W2089938274 hasConcept C12426560 @default.
- W2089938274 hasConcept C126255220 @default.
- W2089938274 hasConcept C127413603 @default.
- W2089938274 hasConcept C134306372 @default.
- W2089938274 hasConcept C137836250 @default.
- W2089938274 hasConcept C14036430 @default.
- W2089938274 hasConcept C154945302 @default.
- W2089938274 hasConcept C167981619 @default.
- W2089938274 hasConcept C177264268 @default.
- W2089938274 hasConcept C187691185 @default.
- W2089938274 hasConcept C199360897 @default.
- W2089938274 hasConcept C201995342 @default.
- W2089938274 hasConcept C2524010 @default.
- W2089938274 hasConcept C2780451532 @default.
- W2089938274 hasConcept C2987595161 @default.
- W2089938274 hasConcept C33923547 @default.
- W2089938274 hasConcept C41008148 @default.
- W2089938274 hasConcept C50644808 @default.
- W2089938274 hasConcept C5917680 @default.
- W2089938274 hasConcept C62520636 @default.
- W2089938274 hasConcept C75782508 @default.
- W2089938274 hasConcept C78458016 @default.
- W2089938274 hasConcept C86803240 @default.
- W2089938274 hasConcept C91873725 @default.
- W2089938274 hasConcept C9679016 @default.
- W2089938274 hasConcept C97541855 @default.
- W2089938274 hasConcept C98036226 @default.
- W2089938274 hasConceptScore W2089938274C106301342 @default.
- W2089938274 hasConceptScore W2089938274C11413529 @default.
- W2089938274 hasConceptScore W2089938274C121332964 @default.
- W2089938274 hasConceptScore W2089938274C12426560 @default.
- W2089938274 hasConceptScore W2089938274C126255220 @default.
- W2089938274 hasConceptScore W2089938274C127413603 @default.
- W2089938274 hasConceptScore W2089938274C134306372 @default.
- W2089938274 hasConceptScore W2089938274C137836250 @default.
- W2089938274 hasConceptScore W2089938274C14036430 @default.
- W2089938274 hasConceptScore W2089938274C154945302 @default.
- W2089938274 hasConceptScore W2089938274C167981619 @default.
- W2089938274 hasConceptScore W2089938274C177264268 @default.
- W2089938274 hasConceptScore W2089938274C187691185 @default.
- W2089938274 hasConceptScore W2089938274C199360897 @default.
- W2089938274 hasConceptScore W2089938274C201995342 @default.
- W2089938274 hasConceptScore W2089938274C2524010 @default.
- W2089938274 hasConceptScore W2089938274C2780451532 @default.
- W2089938274 hasConceptScore W2089938274C2987595161 @default.
- W2089938274 hasConceptScore W2089938274C33923547 @default.
- W2089938274 hasConceptScore W2089938274C41008148 @default.
- W2089938274 hasConceptScore W2089938274C50644808 @default.
- W2089938274 hasConceptScore W2089938274C5917680 @default.
- W2089938274 hasConceptScore W2089938274C62520636 @default.
- W2089938274 hasConceptScore W2089938274C75782508 @default.
- W2089938274 hasConceptScore W2089938274C78458016 @default.
- W2089938274 hasConceptScore W2089938274C86803240 @default.
- W2089938274 hasConceptScore W2089938274C91873725 @default.
- W2089938274 hasConceptScore W2089938274C9679016 @default.
- W2089938274 hasConceptScore W2089938274C97541855 @default.
- W2089938274 hasConceptScore W2089938274C98036226 @default.
- W2089938274 hasLocation W20899382741 @default.
- W2089938274 hasOpenAccess W2089938274 @default.
- W2089938274 hasPrimaryLocation W20899382741 @default.
- W2089938274 hasRelatedWork W1497074676 @default.
- W2089938274 hasRelatedWork W1558926007 @default.
- W2089938274 hasRelatedWork W1599428354 @default.
- W2089938274 hasRelatedWork W1909866182 @default.
- W2089938274 hasRelatedWork W2066423922 @default.
- W2089938274 hasRelatedWork W2073773747 @default.
- W2089938274 hasRelatedWork W2075218162 @default.
- W2089938274 hasRelatedWork W2076803070 @default.
- W2089938274 hasRelatedWork W2090861701 @default.
- W2089938274 hasRelatedWork W2160423747 @default.
- W2089938274 hasRelatedWork W2281804412 @default.
- W2089938274 hasRelatedWork W2327694831 @default.
- W2089938274 hasRelatedWork W2350629169 @default.
- W2089938274 hasRelatedWork W2354950528 @default.
- W2089938274 hasRelatedWork W2610478851 @default.
- W2089938274 hasRelatedWork W2754683881 @default.