Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999621000> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2999621000 abstract "Catastrophic forgetting is a tough challenge when agent attempts to address different tasks sequentially without storing previous information, which gradually hinders the development of continual learning. Except for image classification tasks in continual learning, however, there are little reviews related to robotic manipulation. In this paper, we present a novel hierarchical architecture called Primitives Generation Policy Learning to enable continual learning. More specifically, a generative method by Variational Autoencoder is employed to generate state primitives from task space, then separate policy learning component is designed to learn torque control commands for different tasks sequentially. Furthermore, different task policies could be identified automatically by comparing reconstruction loss in the autoencoder. Experiment on robotic manipulation task shows that the proposed method exhibits substantially improved performance over some other continual learning methods." @default.
- W2999621000 created "2020-01-23" @default.
- W2999621000 creator A5007963696 @default.
- W2999621000 creator A5026022035 @default.
- W2999621000 creator A5056039500 @default.
- W2999621000 creator A5062211930 @default.
- W2999621000 creator A5081774458 @default.
- W2999621000 date "2019-11-01" @default.
- W2999621000 modified "2023-09-27" @default.
- W2999621000 title "Primitives Generation Policy Learning without Catastrophic Forgetting for Robotic Manipulation" @default.
- W2999621000 cites W1596324102 @default.
- W2999621000 cites W1682403713 @default.
- W2999621000 cites W1959608418 @default.
- W2999621000 cites W2060277733 @default.
- W2999621000 cites W2101493843 @default.
- W2999621000 cites W2102605133 @default.
- W2999621000 cites W2104733512 @default.
- W2999621000 cites W2126204609 @default.
- W2999621000 cites W2145339207 @default.
- W2999621000 cites W2473930607 @default.
- W2999621000 cites W2526566391 @default.
- W2999621000 cites W2554616628 @default.
- W2999621000 cites W2560647685 @default.
- W2999621000 cites W2604726708 @default.
- W2999621000 cites W2605043629 @default.
- W2999621000 cites W2761941767 @default.
- W2999621000 cites W2791869553 @default.
- W2999621000 cites W2913340405 @default.
- W2999621000 cites W2919115771 @default.
- W2999621000 cites W2963630259 @default.
- W2999621000 cites W2963794146 @default.
- W2999621000 cites W2968203899 @default.
- W2999621000 cites W3103800629 @default.
- W2999621000 cites W99485931 @default.
- W2999621000 doi "https://doi.org/10.1109/icdmw.2019.00130" @default.
- W2999621000 hasPublicationYear "2019" @default.
- W2999621000 type Work @default.
- W2999621000 sameAs 2999621000 @default.
- W2999621000 citedByCount "0" @default.
- W2999621000 crossrefType "proceedings-article" @default.
- W2999621000 hasAuthorship W2999621000A5007963696 @default.
- W2999621000 hasAuthorship W2999621000A5026022035 @default.
- W2999621000 hasAuthorship W2999621000A5056039500 @default.
- W2999621000 hasAuthorship W2999621000A5062211930 @default.
- W2999621000 hasAuthorship W2999621000A5081774458 @default.
- W2999621000 hasConcept C101738243 @default.
- W2999621000 hasConcept C108583219 @default.
- W2999621000 hasConcept C119857082 @default.
- W2999621000 hasConcept C127413603 @default.
- W2999621000 hasConcept C138885662 @default.
- W2999621000 hasConcept C154945302 @default.
- W2999621000 hasConcept C201995342 @default.
- W2999621000 hasConcept C2775924081 @default.
- W2999621000 hasConcept C2780451532 @default.
- W2999621000 hasConcept C41008148 @default.
- W2999621000 hasConcept C41895202 @default.
- W2999621000 hasConcept C7149132 @default.
- W2999621000 hasConceptScore W2999621000C101738243 @default.
- W2999621000 hasConceptScore W2999621000C108583219 @default.
- W2999621000 hasConceptScore W2999621000C119857082 @default.
- W2999621000 hasConceptScore W2999621000C127413603 @default.
- W2999621000 hasConceptScore W2999621000C138885662 @default.
- W2999621000 hasConceptScore W2999621000C154945302 @default.
- W2999621000 hasConceptScore W2999621000C201995342 @default.
- W2999621000 hasConceptScore W2999621000C2775924081 @default.
- W2999621000 hasConceptScore W2999621000C2780451532 @default.
- W2999621000 hasConceptScore W2999621000C41008148 @default.
- W2999621000 hasConceptScore W2999621000C41895202 @default.
- W2999621000 hasConceptScore W2999621000C7149132 @default.
- W2999621000 hasLocation W29996210001 @default.
- W2999621000 hasOpenAccess W2999621000 @default.
- W2999621000 hasPrimaryLocation W29996210001 @default.
- W2999621000 hasRelatedWork W2771011331 @default.
- W2999621000 hasRelatedWork W2804175194 @default.
- W2999621000 hasRelatedWork W2897239789 @default.
- W2999621000 hasRelatedWork W2962860923 @default.
- W2999621000 hasRelatedWork W2963438784 @default.
- W2999621000 hasRelatedWork W2970502342 @default.
- W2999621000 hasRelatedWork W2980994576 @default.
- W2999621000 hasRelatedWork W2982701845 @default.
- W2999621000 hasRelatedWork W2995269492 @default.
- W2999621000 hasRelatedWork W3002701914 @default.
- W2999621000 hasRelatedWork W3033074320 @default.
- W2999621000 hasRelatedWork W3048263204 @default.
- W2999621000 hasRelatedWork W3103724573 @default.
- W2999621000 hasRelatedWork W3103800629 @default.
- W2999621000 hasRelatedWork W3108827478 @default.
- W2999621000 hasRelatedWork W3122606629 @default.
- W2999621000 hasRelatedWork W3128395934 @default.
- W2999621000 hasRelatedWork W3135512538 @default.
- W2999621000 hasRelatedWork W3198157352 @default.
- W2999621000 hasRelatedWork W3201509095 @default.
- W2999621000 isParatext "false" @default.
- W2999621000 isRetracted "false" @default.
- W2999621000 magId "2999621000" @default.
- W2999621000 workType "article" @default.