Matches in SemOpenAlex for { <https://semopenalex.org/work/W2071444114> ?p ?o ?g. }
- W2071444114 abstract "Temporal abstraction and task decomposition drastically reduce the search space for planning and control, and are fundamental to making complex tasks amenable to learning. In the context of reinforcement learning, temporal abstractions are studied within the paradigm of hierarchical reinforcement learning. We propose a hierarchical reinforcement learning approach by applying our algorithm PI <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> to sequences of Dynamic Movement Primitives. For robots, this representation has some important advantages over discrete representations in terms of scalability and convergence speed. The parameters of the Dynamic Movement Primitives are learned simultaneously at different levels of temporal abstraction. The shape of a movement primitive is optimized w.r.t. the costs up to the next primitive in the sequence, and the subgoals between two movement primitives w.r.t. the costs up to the end of the entire movement primitive sequence. We implement our approach on an 11-DOF arm and hand, and evaluate it in a pick-and-place task in which the robot transports an object between different shelves in a cupboard." @default.
- W2071444114 created "2016-06-24" @default.
- W2071444114 creator A5017689065 @default.
- W2071444114 creator A5029642293 @default.
- W2071444114 date "2011-10-01" @default.
- W2071444114 modified "2023-10-04" @default.
- W2071444114 title "Hierarchical reinforcement learning with movement primitives" @default.
- W2071444114 cites W1556151214 @default.
- W2071444114 cites W1592847719 @default.
- W2071444114 cites W1982803779 @default.
- W2071444114 cites W2105546430 @default.
- W2071444114 cites W2105777811 @default.
- W2071444114 cites W2113698995 @default.
- W2071444114 cites W2116226448 @default.
- W2071444114 cites W2120772693 @default.
- W2071444114 cites W2121518244 @default.
- W2071444114 cites W2147828974 @default.
- W2071444114 cites W2151975555 @default.
- W2071444114 cites W2167647761 @default.
- W2071444114 doi "https://doi.org/10.1109/humanoids.2011.6100841" @default.
- W2071444114 hasPublicationYear "2011" @default.
- W2071444114 type Work @default.
- W2071444114 sameAs 2071444114 @default.
- W2071444114 citedByCount "54" @default.
- W2071444114 countsByYear W20714441142012 @default.
- W2071444114 countsByYear W20714441142013 @default.
- W2071444114 countsByYear W20714441142014 @default.
- W2071444114 countsByYear W20714441142015 @default.
- W2071444114 countsByYear W20714441142016 @default.
- W2071444114 countsByYear W20714441142017 @default.
- W2071444114 countsByYear W20714441142018 @default.
- W2071444114 countsByYear W20714441142019 @default.
- W2071444114 countsByYear W20714441142020 @default.
- W2071444114 countsByYear W20714441142021 @default.
- W2071444114 countsByYear W20714441142022 @default.
- W2071444114 countsByYear W20714441142023 @default.
- W2071444114 crossrefType "proceedings-article" @default.
- W2071444114 hasAuthorship W2071444114A5017689065 @default.
- W2071444114 hasAuthorship W2071444114A5029642293 @default.
- W2071444114 hasConcept C107038049 @default.
- W2071444114 hasConcept C111472728 @default.
- W2071444114 hasConcept C121332964 @default.
- W2071444114 hasConcept C124304363 @default.
- W2071444114 hasConcept C1276947 @default.
- W2071444114 hasConcept C13662910 @default.
- W2071444114 hasConcept C138885662 @default.
- W2071444114 hasConcept C151730666 @default.
- W2071444114 hasConcept C154945302 @default.
- W2071444114 hasConcept C162324750 @default.
- W2071444114 hasConcept C17744445 @default.
- W2071444114 hasConcept C187736073 @default.
- W2071444114 hasConcept C199539241 @default.
- W2071444114 hasConcept C2776359362 @default.
- W2071444114 hasConcept C2777303404 @default.
- W2071444114 hasConcept C2778112365 @default.
- W2071444114 hasConcept C2779343474 @default.
- W2071444114 hasConcept C2780226923 @default.
- W2071444114 hasConcept C2780451532 @default.
- W2071444114 hasConcept C41008148 @default.
- W2071444114 hasConcept C48044578 @default.
- W2071444114 hasConcept C50522688 @default.
- W2071444114 hasConcept C54355233 @default.
- W2071444114 hasConcept C77088390 @default.
- W2071444114 hasConcept C86803240 @default.
- W2071444114 hasConcept C90509273 @default.
- W2071444114 hasConcept C94625758 @default.
- W2071444114 hasConcept C97541855 @default.
- W2071444114 hasConceptScore W2071444114C107038049 @default.
- W2071444114 hasConceptScore W2071444114C111472728 @default.
- W2071444114 hasConceptScore W2071444114C121332964 @default.
- W2071444114 hasConceptScore W2071444114C124304363 @default.
- W2071444114 hasConceptScore W2071444114C1276947 @default.
- W2071444114 hasConceptScore W2071444114C13662910 @default.
- W2071444114 hasConceptScore W2071444114C138885662 @default.
- W2071444114 hasConceptScore W2071444114C151730666 @default.
- W2071444114 hasConceptScore W2071444114C154945302 @default.
- W2071444114 hasConceptScore W2071444114C162324750 @default.
- W2071444114 hasConceptScore W2071444114C17744445 @default.
- W2071444114 hasConceptScore W2071444114C187736073 @default.
- W2071444114 hasConceptScore W2071444114C199539241 @default.
- W2071444114 hasConceptScore W2071444114C2776359362 @default.
- W2071444114 hasConceptScore W2071444114C2777303404 @default.
- W2071444114 hasConceptScore W2071444114C2778112365 @default.
- W2071444114 hasConceptScore W2071444114C2779343474 @default.
- W2071444114 hasConceptScore W2071444114C2780226923 @default.
- W2071444114 hasConceptScore W2071444114C2780451532 @default.
- W2071444114 hasConceptScore W2071444114C41008148 @default.
- W2071444114 hasConceptScore W2071444114C48044578 @default.
- W2071444114 hasConceptScore W2071444114C50522688 @default.
- W2071444114 hasConceptScore W2071444114C54355233 @default.
- W2071444114 hasConceptScore W2071444114C77088390 @default.
- W2071444114 hasConceptScore W2071444114C86803240 @default.
- W2071444114 hasConceptScore W2071444114C90509273 @default.
- W2071444114 hasConceptScore W2071444114C94625758 @default.
- W2071444114 hasConceptScore W2071444114C97541855 @default.
- W2071444114 hasLocation W20714441141 @default.
- W2071444114 hasOpenAccess W2071444114 @default.
- W2071444114 hasPrimaryLocation W20714441141 @default.
- W2071444114 hasRelatedWork W1525643724 @default.
- W2071444114 hasRelatedWork W2068265187 @default.