Matches in SemOpenAlex for { <https://semopenalex.org/work/W3167334575> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3167334575 endingPage "2699" @default.
- W3167334575 startingPage "2685" @default.
- W3167334575 abstract "We analyze a tree search problem with an underlying Markov decision process, in which the goal is to identify the best action at the root that achieves the highest cumulative reward. We present a new tree policy that optimally allocates a limited computing budget to maximize a lower bound on the probability of correctly selecting the best action at each node. Compared to widely used upper confidence bound (UCB) tree policies, the new tree policy presents a more balanced approach to manage the exploration and exploitation tradeoff when the sampling budget is limited. Furthermore, UCB assumes that the support of reward distribution is known, whereas our algorithm relaxes this assumption. Numerical experiments demonstrate the efficiency of our algorithm in selecting the best action at the root." @default.
- W3167334575 created "2021-06-22" @default.
- W3167334575 creator A5000889975 @default.
- W3167334575 creator A5053083043 @default.
- W3167334575 creator A5075059198 @default.
- W3167334575 date "2022-06-01" @default.
- W3167334575 modified "2023-10-17" @default.
- W3167334575 title "An Optimal Computing Budget Allocation Tree Policy for Monte Carlo Tree Search" @default.
- W3167334575 cites W1536615069 @default.
- W3167334575 cites W1625390266 @default.
- W3167334575 cites W1714211023 @default.
- W3167334575 cites W1881419322 @default.
- W3167334575 cites W1967181812 @default.
- W3167334575 cites W2009551863 @default.
- W3167334575 cites W2016647253 @default.
- W3167334575 cites W2038110713 @default.
- W3167334575 cites W2046282120 @default.
- W3167334575 cites W2049934117 @default.
- W3167334575 cites W2126316555 @default.
- W3167334575 cites W2138016587 @default.
- W3167334575 cites W2168405694 @default.
- W3167334575 cites W2257979135 @default.
- W3167334575 cites W2401855953 @default.
- W3167334575 cites W2524229012 @default.
- W3167334575 cites W2606614575 @default.
- W3167334575 cites W2963653944 @default.
- W3167334575 cites W2972635416 @default.
- W3167334575 cites W3011892947 @default.
- W3167334575 cites W3086574084 @default.
- W3167334575 cites W4212953028 @default.
- W3167334575 cites W4237029372 @default.
- W3167334575 doi "https://doi.org/10.1109/tac.2021.3088792" @default.
- W3167334575 hasPublicationYear "2022" @default.
- W3167334575 type Work @default.
- W3167334575 sameAs 3167334575 @default.
- W3167334575 citedByCount "6" @default.
- W3167334575 countsByYear W31673345752022 @default.
- W3167334575 countsByYear W31673345752023 @default.
- W3167334575 crossrefType "journal-article" @default.
- W3167334575 hasAuthorship W3167334575A5000889975 @default.
- W3167334575 hasAuthorship W3167334575A5053083043 @default.
- W3167334575 hasAuthorship W3167334575A5075059198 @default.
- W3167334575 hasBestOaLocation W31673345752 @default.
- W3167334575 hasConcept C105795698 @default.
- W3167334575 hasConcept C106189395 @default.
- W3167334575 hasConcept C113174947 @default.
- W3167334575 hasConcept C11413529 @default.
- W3167334575 hasConcept C125583679 @default.
- W3167334575 hasConcept C126255220 @default.
- W3167334575 hasConcept C127413603 @default.
- W3167334575 hasConcept C134306372 @default.
- W3167334575 hasConcept C159886148 @default.
- W3167334575 hasConcept C19499675 @default.
- W3167334575 hasConcept C207024777 @default.
- W3167334575 hasConcept C33923547 @default.
- W3167334575 hasConcept C41008148 @default.
- W3167334575 hasConcept C46149586 @default.
- W3167334575 hasConcept C62611344 @default.
- W3167334575 hasConcept C66938386 @default.
- W3167334575 hasConceptScore W3167334575C105795698 @default.
- W3167334575 hasConceptScore W3167334575C106189395 @default.
- W3167334575 hasConceptScore W3167334575C113174947 @default.
- W3167334575 hasConceptScore W3167334575C11413529 @default.
- W3167334575 hasConceptScore W3167334575C125583679 @default.
- W3167334575 hasConceptScore W3167334575C126255220 @default.
- W3167334575 hasConceptScore W3167334575C127413603 @default.
- W3167334575 hasConceptScore W3167334575C134306372 @default.
- W3167334575 hasConceptScore W3167334575C159886148 @default.
- W3167334575 hasConceptScore W3167334575C19499675 @default.
- W3167334575 hasConceptScore W3167334575C207024777 @default.
- W3167334575 hasConceptScore W3167334575C33923547 @default.
- W3167334575 hasConceptScore W3167334575C41008148 @default.
- W3167334575 hasConceptScore W3167334575C46149586 @default.
- W3167334575 hasConceptScore W3167334575C62611344 @default.
- W3167334575 hasConceptScore W3167334575C66938386 @default.
- W3167334575 hasFunder F4320332180 @default.
- W3167334575 hasFunder F4320335353 @default.
- W3167334575 hasFunder F4320338279 @default.
- W3167334575 hasIssue "6" @default.
- W3167334575 hasLocation W31673345751 @default.
- W3167334575 hasLocation W31673345752 @default.
- W3167334575 hasOpenAccess W3167334575 @default.
- W3167334575 hasPrimaryLocation W31673345751 @default.
- W3167334575 hasRelatedWork W134727102 @default.
- W3167334575 hasRelatedWork W1990452411 @default.
- W3167334575 hasRelatedWork W2138576994 @default.
- W3167334575 hasRelatedWork W2161367706 @default.
- W3167334575 hasRelatedWork W2963763772 @default.
- W3167334575 hasRelatedWork W3011892947 @default.
- W3167334575 hasRelatedWork W3088333680 @default.
- W3167334575 hasRelatedWork W3167334575 @default.
- W3167334575 hasRelatedWork W3171665292 @default.
- W3167334575 hasRelatedWork W4225011375 @default.
- W3167334575 hasVolume "67" @default.
- W3167334575 isParatext "false" @default.
- W3167334575 isRetracted "false" @default.
- W3167334575 magId "3167334575" @default.
- W3167334575 workType "article" @default.