FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1867103660> ?p ?o ?g. }

• W1867103660 endingPage "334" @default.
• W1867103660 startingPage "320" @default.
• W1867103660 abstract "We study upper and lower bounds on the sample-complexity of learning near-optimal behaviour in finite-state discounted Markov Decision Processes (mdps). We prove a new bound for a modified version of Upper Confidence Reinforcement Learning (ucrl) with only cubic dependence on the horizon. The bound is unimprovable in all parameters except the size of the state/action space, where it depends linearly on the number of non-zero transition probabilities. The lower bound strengthens previous work by being both more general (it applies to all policies) and tighter. The upper and lower bounds match up to logarithmic factors provided the transition matrix is not too dense." @default.
• W1867103660 created "2016-06-24" @default.
• W1867103660 creator A5017031238 @default.
• W1867103660 creator A5073944062 @default.
• W1867103660 date "2012-01-01" @default.
• W1867103660 modified "2023-09-28" @default.
• W1867103660 title "PAC Bounds for Discounted MDPs" @default.
• W1867103660 cites W1988526405 @default.
• W1867103660 cites W2002240881 @default.
• W1867103660 cites W2009551863 @default.
• W1867103660 cites W2082691056 @default.
• W1867103660 cites W2129670787 @default.
• W1867103660 cites W2313791856 @default.
• W1867103660 doi "https://doi.org/10.1007/978-3-642-34106-9_26" @default.
• W1867103660 hasPublicationYear "2012" @default.
• W1867103660 type Work @default.
• W1867103660 sameAs 1867103660 @default.
• W1867103660 citedByCount "148" @default.
• W1867103660 countsByYear W18671036602012 @default.
• W1867103660 countsByYear W18671036602013 @default.
• W1867103660 countsByYear W18671036602014 @default.
• W1867103660 countsByYear W18671036602015 @default.
• W1867103660 countsByYear W18671036602016 @default.
• W1867103660 countsByYear W18671036602017 @default.
• W1867103660 countsByYear W18671036602018 @default.
• W1867103660 countsByYear W18671036602019 @default.
• W1867103660 countsByYear W18671036602020 @default.
• W1867103660 countsByYear W18671036602021 @default.
• W1867103660 countsByYear W18671036602022 @default.
• W1867103660 countsByYear W18671036602023 @default.
• W1867103660 crossrefType "book-chapter" @default.
• W1867103660 hasAuthorship W1867103660A5017031238 @default.
• W1867103660 hasAuthorship W1867103660A5073944062 @default.
• W1867103660 hasBestOaLocation W18671036602 @default.
• W1867103660 hasConcept C105795698 @default.
• W1867103660 hasConcept C106189395 @default.
• W1867103660 hasConcept C106487976 @default.
• W1867103660 hasConcept C111919701 @default.
• W1867103660 hasConcept C126255220 @default.
• W1867103660 hasConcept C134306372 @default.
• W1867103660 hasConcept C138885662 @default.
• W1867103660 hasConcept C154945302 @default.
• W1867103660 hasConcept C159886148 @default.
• W1867103660 hasConcept C185592680 @default.
• W1867103660 hasConcept C2778445095 @default.
• W1867103660 hasConcept C2778572836 @default.
• W1867103660 hasConcept C2780813799 @default.
• W1867103660 hasConcept C28826006 @default.
• W1867103660 hasConcept C33923547 @default.
• W1867103660 hasConcept C39927690 @default.
• W1867103660 hasConcept C41008148 @default.
• W1867103660 hasConcept C41895202 @default.
• W1867103660 hasConcept C43617362 @default.
• W1867103660 hasConcept C49555168 @default.
• W1867103660 hasConcept C72434380 @default.
• W1867103660 hasConcept C77553402 @default.
• W1867103660 hasConcept C97541855 @default.
• W1867103660 hasConcept C98763669 @default.
• W1867103660 hasConceptScore W1867103660C105795698 @default.
• W1867103660 hasConceptScore W1867103660C106189395 @default.
• W1867103660 hasConceptScore W1867103660C106487976 @default.
• W1867103660 hasConceptScore W1867103660C111919701 @default.
• W1867103660 hasConceptScore W1867103660C126255220 @default.
• W1867103660 hasConceptScore W1867103660C134306372 @default.
• W1867103660 hasConceptScore W1867103660C138885662 @default.
• W1867103660 hasConceptScore W1867103660C154945302 @default.
• W1867103660 hasConceptScore W1867103660C159886148 @default.
• W1867103660 hasConceptScore W1867103660C185592680 @default.
• W1867103660 hasConceptScore W1867103660C2778445095 @default.
• W1867103660 hasConceptScore W1867103660C2778572836 @default.
• W1867103660 hasConceptScore W1867103660C2780813799 @default.
• W1867103660 hasConceptScore W1867103660C28826006 @default.
• W1867103660 hasConceptScore W1867103660C33923547 @default.
• W1867103660 hasConceptScore W1867103660C39927690 @default.
• W1867103660 hasConceptScore W1867103660C41008148 @default.
• W1867103660 hasConceptScore W1867103660C41895202 @default.
• W1867103660 hasConceptScore W1867103660C43617362 @default.
• W1867103660 hasConceptScore W1867103660C49555168 @default.
• W1867103660 hasConceptScore W1867103660C72434380 @default.
• W1867103660 hasConceptScore W1867103660C77553402 @default.
• W1867103660 hasConceptScore W1867103660C97541855 @default.
• W1867103660 hasConceptScore W1867103660C98763669 @default.
• W1867103660 hasLocation W18671036601 @default.
• W1867103660 hasLocation W18671036602 @default.
• W1867103660 hasLocation W18671036603 @default.
• W1867103660 hasOpenAccess W1867103660 @default.
• W1867103660 hasPrimaryLocation W18671036601 @default.
• W1867103660 hasRelatedWork W1526654727 @default.
• W1867103660 hasRelatedWork W1850488217 @default.
• W1867103660 hasRelatedWork W1867103660 @default.
• W1867103660 hasRelatedWork W1969276875 @default.
• W1867103660 hasRelatedWork W2120678009 @default.
• W1867103660 hasRelatedWork W2937181779 @default.
• W1867103660 hasRelatedWork W2947128950 @default.
• W1867103660 hasRelatedWork W2950049300 @default.
• W1867103660 hasRelatedWork W3167472281 @default.
• W1867103660 hasRelatedWork W4299895404 @default.
• W1867103660 isParatext "false" @default.

• next