Matches in SemOpenAlex for { <https://semopenalex.org/work/W3036988529> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W3036988529 abstract "We study reinforcement learning in continuous state and action spaces endowed with a metric. We provide a refined analysis of a variant of the algorithm of Sinclair, Banerjee, and Yu (2019) and show that its regret scales with the emph{zooming dimension} of the instance. This parameter, which originates in the bandit literature, captures the size of the subsets of near optimal actions and is always smaller than the covering dimension used in previous analyses. As such, our results are the first provably adaptive guarantees for reinforcement learning in metric spaces." @default.
- W3036988529 created "2020-06-25" @default.
- W3036988529 creator A5015082848 @default.
- W3036988529 creator A5058424592 @default.
- W3036988529 date "2020-06-18" @default.
- W3036988529 modified "2023-09-26" @default.
- W3036988529 title "Provably adaptive reinforcement learning in metric spaces" @default.
- W3036988529 cites W1521084402 @default.
- W3036988529 cites W1747856733 @default.
- W3036988529 cites W2071815241 @default.
- W3036988529 cites W2133419240 @default.
- W3036988529 cites W2148434045 @default.
- W3036988529 cites W2943357710 @default.
- W3036988529 cites W2962723383 @default.
- W3036988529 cites W2963049774 @default.
- W3036988529 cites W2963506504 @default.
- W3036988529 cites W2963582321 @default.
- W3036988529 cites W2964054583 @default.
- W3036988529 cites W2971249033 @default.
- W3036988529 cites W2992545808 @default.
- W3036988529 cites W3009498344 @default.
- W3036988529 cites W3034442282 @default.
- W3036988529 cites W3082652141 @default.
- W3036988529 cites W57706852 @default.
- W3036988529 doi "https://doi.org/10.48550/arxiv.2006.10875" @default.
- W3036988529 hasPublicationYear "2020" @default.
- W3036988529 type Work @default.
- W3036988529 sameAs 3036988529 @default.
- W3036988529 citedByCount "0" @default.
- W3036988529 crossrefType "posted-content" @default.
- W3036988529 hasAuthorship W3036988529A5015082848 @default.
- W3036988529 hasAuthorship W3036988529A5058424592 @default.
- W3036988529 hasBestOaLocation W30369885291 @default.
- W3036988529 hasConcept C114614502 @default.
- W3036988529 hasConcept C118615104 @default.
- W3036988529 hasConcept C119857082 @default.
- W3036988529 hasConcept C120665830 @default.
- W3036988529 hasConcept C121332964 @default.
- W3036988529 hasConcept C124913957 @default.
- W3036988529 hasConcept C15336307 @default.
- W3036988529 hasConcept C154945302 @default.
- W3036988529 hasConcept C15744967 @default.
- W3036988529 hasConcept C162324750 @default.
- W3036988529 hasConcept C176217482 @default.
- W3036988529 hasConcept C198043062 @default.
- W3036988529 hasConcept C21547014 @default.
- W3036988529 hasConcept C2780791683 @default.
- W3036988529 hasConcept C33676613 @default.
- W3036988529 hasConcept C33923547 @default.
- W3036988529 hasConcept C41008148 @default.
- W3036988529 hasConcept C50817715 @default.
- W3036988529 hasConcept C62520636 @default.
- W3036988529 hasConcept C67203356 @default.
- W3036988529 hasConcept C77805123 @default.
- W3036988529 hasConcept C97541855 @default.
- W3036988529 hasConceptScore W3036988529C114614502 @default.
- W3036988529 hasConceptScore W3036988529C118615104 @default.
- W3036988529 hasConceptScore W3036988529C119857082 @default.
- W3036988529 hasConceptScore W3036988529C120665830 @default.
- W3036988529 hasConceptScore W3036988529C121332964 @default.
- W3036988529 hasConceptScore W3036988529C124913957 @default.
- W3036988529 hasConceptScore W3036988529C15336307 @default.
- W3036988529 hasConceptScore W3036988529C154945302 @default.
- W3036988529 hasConceptScore W3036988529C15744967 @default.
- W3036988529 hasConceptScore W3036988529C162324750 @default.
- W3036988529 hasConceptScore W3036988529C176217482 @default.
- W3036988529 hasConceptScore W3036988529C198043062 @default.
- W3036988529 hasConceptScore W3036988529C21547014 @default.
- W3036988529 hasConceptScore W3036988529C2780791683 @default.
- W3036988529 hasConceptScore W3036988529C33676613 @default.
- W3036988529 hasConceptScore W3036988529C33923547 @default.
- W3036988529 hasConceptScore W3036988529C41008148 @default.
- W3036988529 hasConceptScore W3036988529C50817715 @default.
- W3036988529 hasConceptScore W3036988529C62520636 @default.
- W3036988529 hasConceptScore W3036988529C67203356 @default.
- W3036988529 hasConceptScore W3036988529C77805123 @default.
- W3036988529 hasConceptScore W3036988529C97541855 @default.
- W3036988529 hasLocation W30369885291 @default.
- W3036988529 hasOpenAccess W3036988529 @default.
- W3036988529 hasPrimaryLocation W30369885291 @default.
- W3036988529 hasRelatedWork W2103708221 @default.
- W3036988529 hasRelatedWork W2963713569 @default.
- W3036988529 hasRelatedWork W2970623262 @default.
- W3036988529 hasRelatedWork W2972413568 @default.
- W3036988529 hasRelatedWork W3036988529 @default.
- W3036988529 hasRelatedWork W3038270013 @default.
- W3036988529 hasRelatedWork W3105108801 @default.
- W3036988529 hasRelatedWork W3105723692 @default.
- W3036988529 hasRelatedWork W3128250523 @default.
- W3036988529 hasRelatedWork W4297814009 @default.
- W3036988529 isParatext "false" @default.
- W3036988529 isRetracted "false" @default.
- W3036988529 magId "3036988529" @default.
- W3036988529 workType "article" @default.