Matches in SemOpenAlex for { <https://semopenalex.org/work/W2034994237> ?p ?o ?g. }
- W2034994237 endingPage "1081" @default.
- W2034994237 startingPage "1074" @default.
- W2034994237 abstract "We present a general analysis of return maximization in reinforcement learning. This analysis does not require assumptions of Markovianity, stationarity, and ergodicity for the stochastic sequential decision processes of reinforcement learning. Instead, our analysis assumes the asymptotic equipartition property fundamental to information theory, providing a substantially different view from that in the literature. As our main results, we show that return maximization is achieved by the overlap of typical and best sequence sets, and we present a class of stochastic sequential decision processes with the necessary condition for return maximization. We also describe several examples of best sequences in terms of return maximization in the class of stochastic sequential decision processes, which satisfy the necessary condition." @default.
- W2034994237 created "2016-06-24" @default.
- W2034994237 creator A5008161122 @default.
- W2034994237 date "2011-12-01" @default.
- W2034994237 modified "2023-10-06" @default.
- W2034994237 title "An information-theoretic analysis of return maximization in reinforcement learning" @default.
- W2034994237 cites W1496462336 @default.
- W2034994237 cites W1549664537 @default.
- W2034994237 cites W1557517019 @default.
- W2034994237 cites W1559758509 @default.
- W2034994237 cites W1591803298 @default.
- W2034994237 cites W1931792391 @default.
- W2034994237 cites W1965812785 @default.
- W2034994237 cites W1968250327 @default.
- W2034994237 cites W1970091448 @default.
- W2034994237 cites W1975455391 @default.
- W2034994237 cites W1986389067 @default.
- W2034994237 cites W1992679782 @default.
- W2034994237 cites W1995875735 @default.
- W2034994237 cites W2025494293 @default.
- W2034994237 cites W2028145673 @default.
- W2034994237 cites W2041367235 @default.
- W2034994237 cites W2043323813 @default.
- W2034994237 cites W2056339533 @default.
- W2034994237 cites W2071983464 @default.
- W2034994237 cites W2072884346 @default.
- W2034994237 cites W2077343054 @default.
- W2034994237 cites W2099111195 @default.
- W2034994237 cites W2100514829 @default.
- W2034994237 cites W2105078254 @default.
- W2034994237 cites W2106942061 @default.
- W2034994237 cites W2107726111 @default.
- W2034994237 cites W2113501460 @default.
- W2034994237 cites W2116387273 @default.
- W2034994237 cites W2119333483 @default.
- W2034994237 cites W2121863487 @default.
- W2034994237 cites W2126685977 @default.
- W2034994237 cites W2133378540 @default.
- W2034994237 cites W2139474891 @default.
- W2034994237 cites W2147750403 @default.
- W2034994237 cites W2150339816 @default.
- W2034994237 cites W2158091072 @default.
- W2034994237 cites W2162635854 @default.
- W2034994237 cites W2169209873 @default.
- W2034994237 cites W2171630474 @default.
- W2034994237 cites W2341171179 @default.
- W2034994237 cites W2531891978 @default.
- W2034994237 cites W2540085067 @default.
- W2034994237 cites W2914656440 @default.
- W2034994237 cites W32403112 @default.
- W2034994237 cites W79265410 @default.
- W2034994237 cites W2154518298 @default.
- W2034994237 doi "https://doi.org/10.1016/j.neunet.2011.05.002" @default.
- W2034994237 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/21665429" @default.
- W2034994237 hasPublicationYear "2011" @default.
- W2034994237 type Work @default.
- W2034994237 sameAs 2034994237 @default.
- W2034994237 citedByCount "2" @default.
- W2034994237 countsByYear W20349942372017 @default.
- W2034994237 countsByYear W20349942372019 @default.
- W2034994237 crossrefType "journal-article" @default.
- W2034994237 hasAuthorship W2034994237A5008161122 @default.
- W2034994237 hasConcept C105795698 @default.
- W2034994237 hasConcept C111472728 @default.
- W2034994237 hasConcept C126255220 @default.
- W2034994237 hasConcept C127233936 @default.
- W2034994237 hasConcept C138885662 @default.
- W2034994237 hasConcept C154945302 @default.
- W2034994237 hasConcept C189950617 @default.
- W2034994237 hasConcept C201779956 @default.
- W2034994237 hasConcept C2776330181 @default.
- W2034994237 hasConcept C2777212361 @default.
- W2034994237 hasConcept C2778112365 @default.
- W2034994237 hasConcept C33923547 @default.
- W2034994237 hasConcept C41008148 @default.
- W2034994237 hasConcept C54355233 @default.
- W2034994237 hasConcept C8272713 @default.
- W2034994237 hasConcept C86803240 @default.
- W2034994237 hasConcept C9679016 @default.
- W2034994237 hasConcept C97541855 @default.
- W2034994237 hasConceptScore W2034994237C105795698 @default.
- W2034994237 hasConceptScore W2034994237C111472728 @default.
- W2034994237 hasConceptScore W2034994237C126255220 @default.
- W2034994237 hasConceptScore W2034994237C127233936 @default.
- W2034994237 hasConceptScore W2034994237C138885662 @default.
- W2034994237 hasConceptScore W2034994237C154945302 @default.
- W2034994237 hasConceptScore W2034994237C189950617 @default.
- W2034994237 hasConceptScore W2034994237C201779956 @default.
- W2034994237 hasConceptScore W2034994237C2776330181 @default.
- W2034994237 hasConceptScore W2034994237C2777212361 @default.
- W2034994237 hasConceptScore W2034994237C2778112365 @default.
- W2034994237 hasConceptScore W2034994237C33923547 @default.
- W2034994237 hasConceptScore W2034994237C41008148 @default.
- W2034994237 hasConceptScore W2034994237C54355233 @default.
- W2034994237 hasConceptScore W2034994237C8272713 @default.
- W2034994237 hasConceptScore W2034994237C86803240 @default.
- W2034994237 hasConceptScore W2034994237C9679016 @default.
- W2034994237 hasConceptScore W2034994237C97541855 @default.