FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2344778961> ?p ?o ?g. }

• W2344778961 abstract "With reinforcement learning techniques, an agent learns an optimal policy by trial-and-error interaction with an environment. The integration of function approximation methods into reinforcement learning models allows for learning state-action values in large state spaces. Ensemble models can achieve more accurate and robust predictions than single learners. In this work, reinforcement learning ensembles are considered, where the members are artificial neural networks. It is analytically shown that the committees benefit from the diversity on the value estimations. The empirical evaluations on two large state space environments confirmed the theoretical results. A selective ensemble may further improve the predictions by selecting a subset of the models from the entire ensemble. In the thesis, an algorithm for ensemble subset selection is proposed. Experimentally, we found that selecting an informative subset of many agents may be more efficient than training full ensembles. In clustering, a model is built for discovering group-like structures in unobserved data. Over the last years, real-world data sets have become larger. However, an exact-solution model training method may not be able to learn from full large data sets due to the time complexity. Partitioning clustering methods with a linear time complexity can handle large data sets but mostly assume spherically-shaped clusters in the input space. In contrast, kernel-based methods may group the data in arbitrary shapes in the input space, but have a quadratic time complexity. This work focuses on an approximate kernel clustering approach and empirically evaluates it on five real-world data sets. In semi-supervised clustering, external information is partially used for improving the clustering results. A method (SKC) is proposed that exploits the class labels to influence the positions in the centres. In the experiments, SKC outperformed the baseline methods in the external cluster validation measures." @default.
• W2344778961 created "2016-06-24" @default.
• W2344778961 creator A5017452079 @default.
• W2344778961 date "2015-07-14" @default.
• W2344778961 modified "2023-09-23" @default.
• W2344778961 title "Large state spaces and large data: Utilizing neural network ensembles in reinforcement learning and kernel methods for clustering" @default.
• W2344778961 cites W124223554 @default.
• W2344778961 cites W147860157 @default.
• W2344778961 cites W1485158290 @default.
• W2344778961 cites W1487307575 @default.
• W2344778961 cites W1510073064 @default.
• W2344778961 cites W1525612297 @default.
• W2344778961 cites W1550271654 @default.
• W2344778961 cites W1575476631 @default.
• W2344778961 cites W1576452626 @default.
• W2344778961 cites W1592775125 @default.
• W2344778961 cites W1598551017 @default.
• W2344778961 cites W1646707810 @default.
• W2344778961 cites W1673310716 @default.
• W2344778961 cites W168823656 @default.
• W2344778961 cites W1778554682 @default.
• W2344778961 cites W1844779769 @default.
• W2344778961 cites W1969477885 @default.
• W2344778961 cites W1976578332 @default.
• W2344778961 cites W1985059878 @default.
• W2344778961 cites W1986007546 @default.
• W2344778961 cites W1995276998 @default.
• W2344778961 cites W2002978771 @default.
• W2344778961 cites W2011430131 @default.
• W2344778961 cites W2043806097 @default.
• W2344778961 cites W2044074081 @default.
• W2344778961 cites W2050920274 @default.
• W2344778961 cites W2051224630 @default.
• W2344778961 cites W2051856481 @default.
• W2344778961 cites W2055666585 @default.
• W2344778961 cites W2061823973 @default.
• W2344778961 cites W2062989416 @default.
• W2344778961 cites W2075268401 @default.
• W2344778961 cites W2093717447 @default.
• W2344778961 cites W2097645701 @default.
• W2344778961 cites W2100128988 @default.
• W2344778961 cites W2101881799 @default.
• W2344778961 cites W2103496339 @default.
• W2344778961 cites W2107025582 @default.
• W2344778961 cites W2107726111 @default.
• W2344778961 cites W2108596215 @default.
• W2344778961 cites W2109102709 @default.
• W2344778961 cites W2112076978 @default.
• W2344778961 cites W2115665694 @default.
• W2344778961 cites W2120346334 @default.
• W2344778961 cites W2121043290 @default.
• W2344778961 cites W2121863487 @default.
• W2344778961 cites W2123297508 @default.
• W2344778961 cites W2126223576 @default.
• W2344778961 cites W2127218421 @default.
• W2344778961 cites W2129018774 @default.
• W2344778961 cites W2129838208 @default.
• W2344778961 cites W2134042548 @default.
• W2344778961 cites W2134089414 @default.
• W2344778961 cites W2139418546 @default.
• W2344778961 cites W2139956879 @default.
• W2344778961 cites W2140095548 @default.
• W2344778961 cites W2160484893 @default.
• W2344778961 cites W2161278885 @default.
• W2344778961 cites W2171975443 @default.
• W2344778961 cites W2201675152 @default.
• W2344778961 cites W2339916026 @default.
• W2344778961 cites W2341171179 @default.
• W2344778961 cites W2396704156 @default.
• W2344778961 cites W2570107029 @default.
• W2344778961 cites W2751335644 @default.
• W2344778961 cites W2912934387 @default.
• W2344778961 cites W3120740533 @default.
• W2344778961 cites W3139377883 @default.
• W2344778961 cites W87092222 @default.
• W2344778961 cites W2621757076 @default.
• W2344778961 doi "https://doi.org/10.18725/oparu-3241" @default.
• W2344778961 hasPublicationYear "2015" @default.
• W2344778961 type Work @default.
• W2344778961 sameAs 2344778961 @default.
• W2344778961 citedByCount "0" @default.
• W2344778961 crossrefType "dissertation" @default.
• W2344778961 hasAuthorship W2344778961A5017452079 @default.
• W2344778961 hasConcept C105795698 @default.
• W2344778961 hasConcept C114614502 @default.
• W2344778961 hasConcept C119857082 @default.
• W2344778961 hasConcept C154945302 @default.
• W2344778961 hasConcept C33923547 @default.
• W2344778961 hasConcept C41008148 @default.
• W2344778961 hasConcept C45942800 @default.
• W2344778961 hasConcept C50644808 @default.
• W2344778961 hasConcept C72434380 @default.
• W2344778961 hasConcept C73555534 @default.
• W2344778961 hasConcept C74193536 @default.
• W2344778961 hasConcept C91873725 @default.
• W2344778961 hasConcept C97541855 @default.
• W2344778961 hasConceptScore W2344778961C105795698 @default.
• W2344778961 hasConceptScore W2344778961C114614502 @default.
• W2344778961 hasConceptScore W2344778961C119857082 @default.
• W2344778961 hasConceptScore W2344778961C154945302 @default.

• next