Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210256054> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4210256054 endingPage "3663" @default.
- W4210256054 startingPage "3656" @default.
- W4210256054 abstract "Adapting the mastered manipulation skill to novel objects is still challenging for robots. Recent works have attempted to endow the robot with the ability to adapt to unseen tasks by leveraging meta-learning. However, these methods are data-hungry in the training phase, which limits their application in the real world. In this paper, we propose Meta-Residual Policy Learning (MRPL) to reduce the cost of policy learning and adaptation. During meta-training, MRPL accelerates the learning process by focusing on the residual task-shared knowledge that is hard to be embedded in the hand-engineered controller. During testing, MRPL achieves fast adaptation on similar unseen tasks through fusing task-specific knowledge in the demonstration with task-shared knowledge in the learned policy. We conduct a series of simulated and real-world peg-in-hole tasks to evaluate the proposed method. The experimental results demonstrate that MRPL outperforms prior methods in robot skill adaptation. Code for this work is available at <uri xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>https://github.com/Bartopt/code4MRPL</uri> ." @default.
- W4210256054 created "2022-02-08" @default.
- W4210256054 creator A5019570425 @default.
- W4210256054 creator A5028503217 @default.
- W4210256054 creator A5050146220 @default.
- W4210256054 creator A5055167945 @default.
- W4210256054 creator A5088116668 @default.
- W4210256054 creator A5089404454 @default.
- W4210256054 date "2022-04-01" @default.
- W4210256054 modified "2023-10-15" @default.
- W4210256054 title "Meta-Residual Policy Learning: Zero-Trial Robot Skill Adaptation via Knowledge Fusion" @default.
- W4210256054 cites W2010474504 @default.
- W4210256054 cites W2164474021 @default.
- W4210256054 cites W2781935341 @default.
- W4210256054 cites W2890218953 @default.
- W4210256054 cites W2963099939 @default.
- W4210256054 cites W2967727187 @default.
- W4210256054 cites W2968268581 @default.
- W4210256054 cites W2979952733 @default.
- W4210256054 cites W3009295642 @default.
- W4210256054 cites W3130717831 @default.
- W4210256054 cites W3133214370 @default.
- W4210256054 cites W3134395475 @default.
- W4210256054 cites W3164862896 @default.
- W4210256054 cites W3169408498 @default.
- W4210256054 cites W3174364619 @default.
- W4210256054 cites W3176397544 @default.
- W4210256054 cites W3207359859 @default.
- W4210256054 cites W4235715501 @default.
- W4210256054 cites W4248308907 @default.
- W4210256054 doi "https://doi.org/10.1109/lra.2022.3146916" @default.
- W4210256054 hasPublicationYear "2022" @default.
- W4210256054 type Work @default.
- W4210256054 citedByCount "4" @default.
- W4210256054 countsByYear W42102560542022 @default.
- W4210256054 countsByYear W42102560542023 @default.
- W4210256054 crossrefType "journal-article" @default.
- W4210256054 hasAuthorship W4210256054A5019570425 @default.
- W4210256054 hasAuthorship W4210256054A5028503217 @default.
- W4210256054 hasAuthorship W4210256054A5050146220 @default.
- W4210256054 hasAuthorship W4210256054A5055167945 @default.
- W4210256054 hasAuthorship W4210256054A5088116668 @default.
- W4210256054 hasAuthorship W4210256054A5089404454 @default.
- W4210256054 hasConcept C111919701 @default.
- W4210256054 hasConcept C11413529 @default.
- W4210256054 hasConcept C119857082 @default.
- W4210256054 hasConcept C120665830 @default.
- W4210256054 hasConcept C121332964 @default.
- W4210256054 hasConcept C127413603 @default.
- W4210256054 hasConcept C139807058 @default.
- W4210256054 hasConcept C154945302 @default.
- W4210256054 hasConcept C155512373 @default.
- W4210256054 hasConcept C201995342 @default.
- W4210256054 hasConcept C2780451532 @default.
- W4210256054 hasConcept C2781002164 @default.
- W4210256054 hasConcept C41008148 @default.
- W4210256054 hasConcept C90509273 @default.
- W4210256054 hasConcept C98045186 @default.
- W4210256054 hasConceptScore W4210256054C111919701 @default.
- W4210256054 hasConceptScore W4210256054C11413529 @default.
- W4210256054 hasConceptScore W4210256054C119857082 @default.
- W4210256054 hasConceptScore W4210256054C120665830 @default.
- W4210256054 hasConceptScore W4210256054C121332964 @default.
- W4210256054 hasConceptScore W4210256054C127413603 @default.
- W4210256054 hasConceptScore W4210256054C139807058 @default.
- W4210256054 hasConceptScore W4210256054C154945302 @default.
- W4210256054 hasConceptScore W4210256054C155512373 @default.
- W4210256054 hasConceptScore W4210256054C201995342 @default.
- W4210256054 hasConceptScore W4210256054C2780451532 @default.
- W4210256054 hasConceptScore W4210256054C2781002164 @default.
- W4210256054 hasConceptScore W4210256054C41008148 @default.
- W4210256054 hasConceptScore W4210256054C90509273 @default.
- W4210256054 hasConceptScore W4210256054C98045186 @default.
- W4210256054 hasFunder F4320321001 @default.
- W4210256054 hasFunder F4320321133 @default.
- W4210256054 hasIssue "2" @default.
- W4210256054 hasLocation W42102560541 @default.
- W4210256054 hasOpenAccess W4210256054 @default.
- W4210256054 hasPrimaryLocation W42102560541 @default.
- W4210256054 hasRelatedWork W2498789492 @default.
- W4210256054 hasRelatedWork W2521347458 @default.
- W4210256054 hasRelatedWork W2560215812 @default.
- W4210256054 hasRelatedWork W2788972299 @default.
- W4210256054 hasRelatedWork W2925692864 @default.
- W4210256054 hasRelatedWork W2997567050 @default.
- W4210256054 hasRelatedWork W3213722473 @default.
- W4210256054 hasRelatedWork W4233449973 @default.
- W4210256054 hasRelatedWork W2729981612 @default.
- W4210256054 hasRelatedWork W2949601986 @default.
- W4210256054 hasVolume "7" @default.
- W4210256054 isParatext "false" @default.
- W4210256054 isRetracted "false" @default.
- W4210256054 workType "article" @default.