FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136757919> ?p ?o ?g. }

• W3136757919 endingPage "12390" @default.
• W3136757919 startingPage "12382" @default.
• W3136757919 abstract "The use of a policy and a heuristic function for guiding search can be quite effective in adversarial problems, as demonstrated by AlphaGo and its successors, which are based on the PUCT search algorithm. While PUCT can also be used to solve single-agent deterministic problems, it lacks guarantees on its search effort and it can be computationally inefficient in practice. Combining the A* algorithm with a learned heuristic function tends to work better in these domains, but A* and its variants do not use a policy. Moreover, the purpose of using A* is to find solutions of minimum cost, while we seek instead to minimize the search loss (e.g., the number of search steps). LevinTS is guided by a policy and provides guarantees on the number of search steps that relate to the quality of the policy, but it does not make use of a heuristic function. In this work we introduce Policy-guided Heuristic Search (PHS), a novel search algorithm that uses both a heuristic function and a policy and has theoretical guarantees on the search loss that relates to both the quality of the heuristic and of the policy. We show empirically on the sliding-tile puzzle, Sokoban, and a puzzle from the commercial game `The Witness' that PHS enables the rapid learning of both a policy and a heuristic function and compares favorably with A*, Weighted A*, Greedy Best-First Search, LevinTS, and PUCT in terms of number of problems solved and search time in all three domains tested." @default.
• W3136757919 created "2021-03-29" @default.
• W3136757919 creator A5012035228 @default.
• W3136757919 creator A5081226725 @default.
• W3136757919 date "2021-05-18" @default.
• W3136757919 modified "2023-10-16" @default.
• W3136757919 title "Policy-Guided Heuristic Search with Guarantees" @default.
• W3136757919 cites W1555005026 @default.
• W3136757919 cites W1714211023 @default.
• W3136757919 cites W1775783412 @default.
• W3136757919 cites W1969483458 @default.
• W3136757919 cites W1977989560 @default.
• W3136757919 cites W2016647253 @default.
• W3136757919 cites W2016820997 @default.
• W3136757919 cites W2035601288 @default.
• W3136757919 cites W2126677653 @default.
• W3136757919 cites W2150470619 @default.
• W3136757919 cites W2155675331 @default.
• W3136757919 cites W2158118484 @default.
• W3136757919 cites W2257979135 @default.
• W3136757919 cites W2575334674 @default.
• W3136757919 cites W2772709170 @default.
• W3136757919 cites W2960567166 @default.
• W3136757919 cites W2962893049 @default.
• W3136757919 cites W2964121744 @default.
• W3136757919 cites W2965497662 @default.
• W3136757919 cites W3034413776 @default.
• W3136757919 cites W3106271432 @default.
• W3136757919 cites W2922212713 @default.
• W3136757919 doi "https://doi.org/10.1609/aaai.v35i14.17469" @default.
• W3136757919 hasPublicationYear "2021" @default.
• W3136757919 type Work @default.
• W3136757919 sameAs 3136757919 @default.
• W3136757919 citedByCount "2" @default.
• W3136757919 countsByYear W31367579192021 @default.
• W3136757919 crossrefType "journal-article" @default.
• W3136757919 hasAuthorship W3136757919A5012035228 @default.
• W3136757919 hasAuthorship W3136757919A5081226725 @default.
• W3136757919 hasBestOaLocation W31367579191 @default.
• W3136757919 hasConcept C111472728 @default.
• W3136757919 hasConcept C11413529 @default.
• W3136757919 hasConcept C114290370 @default.
• W3136757919 hasConcept C125583679 @default.
• W3136757919 hasConcept C126255220 @default.
• W3136757919 hasConcept C135320971 @default.
• W3136757919 hasConcept C138885662 @default.
• W3136757919 hasConcept C139979381 @default.
• W3136757919 hasConcept C14036430 @default.
• W3136757919 hasConcept C162324750 @default.
• W3136757919 hasConcept C173801870 @default.
• W3136757919 hasConcept C175444787 @default.
• W3136757919 hasConcept C19889080 @default.
• W3136757919 hasConcept C21782646 @default.
• W3136757919 hasConcept C2779530757 @default.
• W3136757919 hasConcept C33923547 @default.
• W3136757919 hasConcept C41008148 @default.
• W3136757919 hasConcept C46011968 @default.
• W3136757919 hasConcept C78458016 @default.
• W3136757919 hasConcept C831591 @default.
• W3136757919 hasConcept C86803240 @default.
• W3136757919 hasConceptScore W3136757919C111472728 @default.
• W3136757919 hasConceptScore W3136757919C11413529 @default.
• W3136757919 hasConceptScore W3136757919C114290370 @default.
• W3136757919 hasConceptScore W3136757919C125583679 @default.
• W3136757919 hasConceptScore W3136757919C126255220 @default.
• W3136757919 hasConceptScore W3136757919C135320971 @default.
• W3136757919 hasConceptScore W3136757919C138885662 @default.
• W3136757919 hasConceptScore W3136757919C139979381 @default.
• W3136757919 hasConceptScore W3136757919C14036430 @default.
• W3136757919 hasConceptScore W3136757919C162324750 @default.
• W3136757919 hasConceptScore W3136757919C173801870 @default.
• W3136757919 hasConceptScore W3136757919C175444787 @default.
• W3136757919 hasConceptScore W3136757919C19889080 @default.
• W3136757919 hasConceptScore W3136757919C21782646 @default.
• W3136757919 hasConceptScore W3136757919C2779530757 @default.
• W3136757919 hasConceptScore W3136757919C33923547 @default.
• W3136757919 hasConceptScore W3136757919C41008148 @default.
• W3136757919 hasConceptScore W3136757919C46011968 @default.
• W3136757919 hasConceptScore W3136757919C78458016 @default.
• W3136757919 hasConceptScore W3136757919C831591 @default.
• W3136757919 hasConceptScore W3136757919C86803240 @default.
• W3136757919 hasIssue "14" @default.
• W3136757919 hasLocation W31367579191 @default.
• W3136757919 hasLocation W31367579192 @default.
• W3136757919 hasOpenAccess W3136757919 @default.
• W3136757919 hasPrimaryLocation W31367579191 @default.
• W3136757919 hasRelatedWork W1622225657 @default.
• W3136757919 hasRelatedWork W2081821176 @default.
• W3136757919 hasRelatedWork W2146477540 @default.
• W3136757919 hasRelatedWork W2183220040 @default.
• W3136757919 hasRelatedWork W2358427436 @default.
• W3136757919 hasRelatedWork W2402589461 @default.
• W3136757919 hasRelatedWork W2747118187 @default.
• W3136757919 hasRelatedWork W3111117784 @default.
• W3136757919 hasRelatedWork W3136757919 @default.
• W3136757919 hasRelatedWork W3176407006 @default.
• W3136757919 hasVolume "35" @default.
• W3136757919 isParatext "false" @default.

• next