FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2125510930> ?p ?o ?g. }

• W2125510930 endingPage "368" @default.
• W2125510930 startingPage "361" @default.
• W2125510930 abstract "It is widely accepted that the use of more compact representations than lookup tables is crucial to scaling reinforcement learning (RL) algorithms to real-world problems. Unfortunately almost all of the theory of reinforcement learning assumes lookup table representations. In this paper we address the pressing issue of combining function approximation and RL, and present 1) a function approximator based on a simple extension to state aggregation (a commonly used form of compact representation), namely soft state aggregation, 2) a theory of convergence for RL with arbitrary, but fixed, soft state aggregation, 3) a novel intuitive understanding of the effect of state aggregation on online RL, and 4) a new heuristic adaptive state aggregation algorithm that finds improved compact representations by exploiting the non-discrete nature of soft state aggregation. Preliminary empirical results are also presented." @default.
• W2125510930 created "2016-06-24" @default.
• W2125510930 creator A5048915657 @default.
• W2125510930 creator A5049812527 @default.
• W2125510930 creator A5065366930 @default.
• W2125510930 date "1994-01-01" @default.
• W2125510930 modified "2023-10-14" @default.
• W2125510930 title "Reinforcement Learning with Soft State Aggregation" @default.
• W2125510930 cites W111328409 @default.
• W2125510930 cites W1541084404 @default.
• W2125510930 cites W1545148916 @default.
• W2125510930 cites W1965227651 @default.
• W2125510930 cites W2048376081 @default.
• W2125510930 cites W2091565802 @default.
• W2125510930 cites W2100677568 @default.
• W2125510930 cites W2121832485 @default.
• W2125510930 cites W2147750403 @default.
• W2125510930 cites W2158091072 @default.
• W2125510930 cites W2165131254 @default.
• W2125510930 cites W17303806 @default.
• W2125510930 hasPublicationYear "1994" @default.
• W2125510930 type Work @default.
• W2125510930 sameAs 2125510930 @default.
• W2125510930 citedByCount "169" @default.
• W2125510930 countsByYear W21255109302012 @default.
• W2125510930 countsByYear W21255109302013 @default.
• W2125510930 countsByYear W21255109302014 @default.
• W2125510930 countsByYear W21255109302015 @default.
• W2125510930 countsByYear W21255109302016 @default.
• W2125510930 countsByYear W21255109302017 @default.
• W2125510930 countsByYear W21255109302018 @default.
• W2125510930 countsByYear W21255109302019 @default.
• W2125510930 countsByYear W21255109302020 @default.
• W2125510930 countsByYear W21255109302021 @default.
• W2125510930 countsByYear W21255109302023 @default.
• W2125510930 crossrefType "proceedings-article" @default.
• W2125510930 hasAuthorship W2125510930A5048915657 @default.
• W2125510930 hasAuthorship W2125510930A5049812527 @default.
• W2125510930 hasAuthorship W2125510930A5065366930 @default.
• W2125510930 hasConcept C11413529 @default.
• W2125510930 hasConcept C14036430 @default.
• W2125510930 hasConcept C154945302 @default.
• W2125510930 hasConcept C162324750 @default.
• W2125510930 hasConcept C173801870 @default.
• W2125510930 hasConcept C17744445 @default.
• W2125510930 hasConcept C199539241 @default.
• W2125510930 hasConcept C2776359362 @default.
• W2125510930 hasConcept C2777303404 @default.
• W2125510930 hasConcept C41008148 @default.
• W2125510930 hasConcept C48103436 @default.
• W2125510930 hasConcept C50522688 @default.
• W2125510930 hasConcept C50644808 @default.
• W2125510930 hasConcept C78458016 @default.
• W2125510930 hasConcept C80444323 @default.
• W2125510930 hasConcept C86803240 @default.
• W2125510930 hasConcept C91873725 @default.
• W2125510930 hasConcept C94625758 @default.
• W2125510930 hasConcept C97541855 @default.
• W2125510930 hasConceptScore W2125510930C11413529 @default.
• W2125510930 hasConceptScore W2125510930C14036430 @default.
• W2125510930 hasConceptScore W2125510930C154945302 @default.
• W2125510930 hasConceptScore W2125510930C162324750 @default.
• W2125510930 hasConceptScore W2125510930C173801870 @default.
• W2125510930 hasConceptScore W2125510930C17744445 @default.
• W2125510930 hasConceptScore W2125510930C199539241 @default.
• W2125510930 hasConceptScore W2125510930C2776359362 @default.
• W2125510930 hasConceptScore W2125510930C2777303404 @default.
• W2125510930 hasConceptScore W2125510930C41008148 @default.
• W2125510930 hasConceptScore W2125510930C48103436 @default.
• W2125510930 hasConceptScore W2125510930C50522688 @default.
• W2125510930 hasConceptScore W2125510930C50644808 @default.
• W2125510930 hasConceptScore W2125510930C78458016 @default.
• W2125510930 hasConceptScore W2125510930C80444323 @default.
• W2125510930 hasConceptScore W2125510930C86803240 @default.
• W2125510930 hasConceptScore W2125510930C91873725 @default.
• W2125510930 hasConceptScore W2125510930C94625758 @default.
• W2125510930 hasConceptScore W2125510930C97541855 @default.
• W2125510930 hasLocation W21255109301 @default.
• W2125510930 hasOpenAccess W2125510930 @default.
• W2125510930 hasPrimaryLocation W21255109301 @default.
• W2125510930 hasRelatedWork W1515851193 @default.
• W2125510930 hasRelatedWork W1547105496 @default.
• W2125510930 hasRelatedWork W1550698229 @default.
• W2125510930 hasRelatedWork W1576452626 @default.
• W2125510930 hasRelatedWork W1646707810 @default.
• W2125510930 hasRelatedWork W2091565802 @default.
• W2125510930 hasRelatedWork W2098432798 @default.
• W2125510930 hasRelatedWork W2100677568 @default.
• W2125510930 hasRelatedWork W2101167844 @default.
• W2125510930 hasRelatedWork W2107726111 @default.
• W2125510930 hasRelatedWork W2119567691 @default.
• W2125510930 hasRelatedWork W2121863487 @default.
• W2125510930 hasRelatedWork W2124175081 @default.
• W2125510930 hasRelatedWork W2125074935 @default.
• W2125510930 hasRelatedWork W2139418546 @default.
• W2125510930 hasRelatedWork W2155027007 @default.
• W2125510930 hasRelatedWork W2165131254 @default.
• W2125510930 hasRelatedWork W2169982856 @default.

• next