Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207627850> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W3207627850 abstract "Creating a domain model, even for classical, domain-independent planning, is a notoriously hard knowledge-engineering task. A natural approach to solve this problem is to learn a domain model from observations. However, model learning approaches frequently do not provide safety guarantees: the learned model may assume actions are applicable when they are not, and may incorrectly capture actions' effects. This may result in generating plans that will fail when executed. In some domains such failures are not acceptable, due to the cost of failure or inability to replan online after failure. In such settings, all learning must be done offline, based on some observations collected, e.g., by some other agents or a human. Through this learning, the task is to generate a plan that is guaranteed to be successful. This is called the model-free planning problem. Prior work proposed an algorithm for solving the model-free planning problem in classical planning. However, they were limited to learning grounded domains, and thus they could not scale. We generalize this prior work and propose the first safe model-free planning algorithm for lifted domains. We prove the correctness of our approach, and provide a statistical analysis showing that the number of trajectories needed to solve future problems with high probability is linear in the potential size of the domain model. We also present experiments on twelve IPC domains showing that our approach is able to learn the real action model in all cases with at most two trajectories." @default.
- W3207627850 created "2021-10-25" @default.
- W3207627850 creator A5031817060 @default.
- W3207627850 creator A5064954992 @default.
- W3207627850 creator A5085970582 @default.
- W3207627850 date "2021-09-01" @default.
- W3207627850 modified "2023-10-16" @default.
- W3207627850 title "Safe Learning of Lifted Action Models" @default.
- W3207627850 doi "https://doi.org/10.24963/kr.2021/36" @default.
- W3207627850 hasPublicationYear "2021" @default.
- W3207627850 type Work @default.
- W3207627850 sameAs 3207627850 @default.
- W3207627850 citedByCount "0" @default.
- W3207627850 crossrefType "proceedings-article" @default.
- W3207627850 hasAuthorship W3207627850A5031817060 @default.
- W3207627850 hasAuthorship W3207627850A5064954992 @default.
- W3207627850 hasAuthorship W3207627850A5085970582 @default.
- W3207627850 hasBestOaLocation W32076278502 @default.
- W3207627850 hasConcept C11413529 @default.
- W3207627850 hasConcept C119857082 @default.
- W3207627850 hasConcept C121332964 @default.
- W3207627850 hasConcept C127413603 @default.
- W3207627850 hasConcept C134306372 @default.
- W3207627850 hasConcept C154945302 @default.
- W3207627850 hasConcept C166957645 @default.
- W3207627850 hasConcept C201995342 @default.
- W3207627850 hasConcept C207685749 @default.
- W3207627850 hasConcept C2776505523 @default.
- W3207627850 hasConcept C2780451532 @default.
- W3207627850 hasConcept C2780791683 @default.
- W3207627850 hasConcept C33923547 @default.
- W3207627850 hasConcept C36503486 @default.
- W3207627850 hasConcept C41008148 @default.
- W3207627850 hasConcept C55439883 @default.
- W3207627850 hasConcept C62520636 @default.
- W3207627850 hasConcept C95457728 @default.
- W3207627850 hasConceptScore W3207627850C11413529 @default.
- W3207627850 hasConceptScore W3207627850C119857082 @default.
- W3207627850 hasConceptScore W3207627850C121332964 @default.
- W3207627850 hasConceptScore W3207627850C127413603 @default.
- W3207627850 hasConceptScore W3207627850C134306372 @default.
- W3207627850 hasConceptScore W3207627850C154945302 @default.
- W3207627850 hasConceptScore W3207627850C166957645 @default.
- W3207627850 hasConceptScore W3207627850C201995342 @default.
- W3207627850 hasConceptScore W3207627850C207685749 @default.
- W3207627850 hasConceptScore W3207627850C2776505523 @default.
- W3207627850 hasConceptScore W3207627850C2780451532 @default.
- W3207627850 hasConceptScore W3207627850C2780791683 @default.
- W3207627850 hasConceptScore W3207627850C33923547 @default.
- W3207627850 hasConceptScore W3207627850C36503486 @default.
- W3207627850 hasConceptScore W3207627850C41008148 @default.
- W3207627850 hasConceptScore W3207627850C55439883 @default.
- W3207627850 hasConceptScore W3207627850C62520636 @default.
- W3207627850 hasConceptScore W3207627850C95457728 @default.
- W3207627850 hasLocation W32076278501 @default.
- W3207627850 hasLocation W32076278502 @default.
- W3207627850 hasOpenAccess W3207627850 @default.
- W3207627850 hasPrimaryLocation W32076278501 @default.
- W3207627850 hasRelatedWork W1525380347 @default.
- W3207627850 hasRelatedWork W1985059659 @default.
- W3207627850 hasRelatedWork W2040828270 @default.
- W3207627850 hasRelatedWork W2158321484 @default.
- W3207627850 hasRelatedWork W2269177343 @default.
- W3207627850 hasRelatedWork W2402104486 @default.
- W3207627850 hasRelatedWork W3102844644 @default.
- W3207627850 hasRelatedWork W3193009145 @default.
- W3207627850 hasRelatedWork W3207101903 @default.
- W3207627850 hasRelatedWork W4283802406 @default.
- W3207627850 isParatext "false" @default.
- W3207627850 isRetracted "false" @default.
- W3207627850 magId "3207627850" @default.
- W3207627850 workType "article" @default.