Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949878712> ?p ?o ?g. }
Showing items 1 to 49 of
49
with 100 items per page.
- W2949878712 abstract "While a large body of empirical results show that temporally-extended actions and options may significantly affect the learning performance of an agent, the theoretical understanding of how and when options can be beneficial in online reinforcement learning is relatively limited. In this paper, we derive an upper and lower bound on the regret of a variant of UCRL using options. While we first analyze the algorithm in the general case of semi-Markov decision processes (SMDPs), we show how these results can be translated to the specific case of MDPs with options and we illustrate simple scenarios in which the regret of learning with options can be textit{provably} much smaller than the regret suffered when learning with primitive actions." @default.
- W2949878712 created "2019-06-27" @default.
- W2949878712 creator A5008246659 @default.
- W2949878712 creator A5014791481 @default.
- W2949878712 date "2017-04-20" @default.
- W2949878712 modified "2023-09-27" @default.
- W2949878712 title "Exploration–Exploitation in MDPs with Options" @default.
- W2949878712 cites W1515851193 @default.
- W2949878712 cites W1536990779 @default.
- W2949878712 cites W1553101044 @default.
- W2949878712 cites W1968768508 @default.
- W2949878712 cites W2107037985 @default.
- W2949878712 cites W2111020392 @default.
- W2949878712 cites W2119567691 @default.
- W2949878712 cites W2121517924 @default.
- W2949878712 cites W2133458291 @default.
- W2949878712 cites W2143435603 @default.
- W2949878712 cites W2155355065 @default.
- W2949878712 cites W2912453235 @default.
- W2949878712 hasPublicationYear "2017" @default.
- W2949878712 type Work @default.
- W2949878712 sameAs 2949878712 @default.
- W2949878712 citedByCount "2" @default.
- W2949878712 countsByYear W29498787122018 @default.
- W2949878712 crossrefType "proceedings-article" @default.
- W2949878712 hasAuthorship W2949878712A5008246659 @default.
- W2949878712 hasAuthorship W2949878712A5014791481 @default.
- W2949878712 hasBestOaLocation W29498787121 @default.
- W2949878712 hasConcept C41008148 @default.
- W2949878712 hasConceptScore W2949878712C41008148 @default.
- W2949878712 hasLocation W29498787121 @default.
- W2949878712 hasLocation W29498787122 @default.
- W2949878712 hasLocation W29498787123 @default.
- W2949878712 hasOpenAccess W2949878712 @default.
- W2949878712 hasPrimaryLocation W29498787121 @default.
- W2949878712 hasRelatedWork W1596801655 @default.
- W2949878712 hasRelatedWork W2130043461 @default.
- W2949878712 hasRelatedWork W2350741829 @default.
- W2949878712 hasRelatedWork W2358668433 @default.
- W2949878712 hasRelatedWork W2376932109 @default.
- W2949878712 hasRelatedWork W2382290278 @default.
- W2949878712 hasRelatedWork W2390279801 @default.
- W2949878712 hasRelatedWork W2748952813 @default.
- W2949878712 hasRelatedWork W2899084033 @default.
- W2949878712 hasRelatedWork W2530322880 @default.
- W2949878712 isParatext "false" @default.
- W2949878712 isRetracted "false" @default.
- W2949878712 magId "2949878712" @default.
- W2949878712 workType "article" @default.