Matches in SemOpenAlex for { <https://semopenalex.org/work/W3009331570> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3009331570 endingPage "3619" @default.
- W3009331570 startingPage "3612" @default.
- W3009331570 abstract "Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncertainty, which makes exploration and constraint satisfaction challenging. We address these issues with a new model-based reinforcement learning algorithm, Safety Augmented Value Estimation from Demonstrations (SAVED), which uses supervision that only identifies task completion and a modest set of suboptimal demonstrations to constrain exploration and learn efficiently while handling complex constraints. We then compare SAVED with 3 state-of-the-art model-based and model-free RL algorithms on 6 standard simulation benchmarks involving navigation and manipulation and a physical knot-tying task on the da Vinci surgical robot. Results suggest that SAVED outperforms prior methods in terms of success rate, constraint satisfaction, and sample efficiency, making it feasible to safely learn a control policy directly on a real robot in less than an hour. For tasks on the robot, baselines succeed less than 5% of the time while SAVED has a success rate of over 75% in the first 50 training iterations. Code and supplementary material is available at https://tinyurl.com/saved-rl." @default.
- W3009331570 created "2020-03-13" @default.
- W3009331570 creator A5016270029 @default.
- W3009331570 creator A5025067440 @default.
- W3009331570 creator A5026281392 @default.
- W3009331570 creator A5026322200 @default.
- W3009331570 creator A5050342525 @default.
- W3009331570 creator A5055891784 @default.
- W3009331570 creator A5071898762 @default.
- W3009331570 creator A5072427753 @default.
- W3009331570 date "2020-04-01" @default.
- W3009331570 modified "2023-09-29" @default.
- W3009331570 title "Safety Augmented Value Estimation From Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks" @default.
- W3009331570 cites W2041242313 @default.
- W3009331570 cites W2061417916 @default.
- W3009331570 cites W2062843008 @default.
- W3009331570 cites W2152536965 @default.
- W3009331570 cites W2281096776 @default.
- W3009331570 cites W2749680651 @default.
- W3009331570 cites W2887709062 @default.
- W3009331570 cites W2911794543 @default.
- W3009331570 cites W2962872206 @default.
- W3009331570 cites W2963099939 @default.
- W3009331570 cites W2963280855 @default.
- W3009331570 cites W2963553847 @default.
- W3009331570 cites W2963598509 @default.
- W3009331570 cites W2963683522 @default.
- W3009331570 cites W3011432977 @default.
- W3009331570 doi "https://doi.org/10.1109/lra.2020.2976272" @default.
- W3009331570 hasPublicationYear "2020" @default.
- W3009331570 type Work @default.
- W3009331570 sameAs 3009331570 @default.
- W3009331570 citedByCount "63" @default.
- W3009331570 countsByYear W30093315702020 @default.
- W3009331570 countsByYear W30093315702021 @default.
- W3009331570 countsByYear W30093315702022 @default.
- W3009331570 countsByYear W30093315702023 @default.
- W3009331570 crossrefType "journal-article" @default.
- W3009331570 hasAuthorship W3009331570A5016270029 @default.
- W3009331570 hasAuthorship W3009331570A5025067440 @default.
- W3009331570 hasAuthorship W3009331570A5026281392 @default.
- W3009331570 hasAuthorship W3009331570A5026322200 @default.
- W3009331570 hasAuthorship W3009331570A5050342525 @default.
- W3009331570 hasAuthorship W3009331570A5055891784 @default.
- W3009331570 hasAuthorship W3009331570A5071898762 @default.
- W3009331570 hasAuthorship W3009331570A5072427753 @default.
- W3009331570 hasBestOaLocation W30093315702 @default.
- W3009331570 hasConcept C119857082 @default.
- W3009331570 hasConcept C127413603 @default.
- W3009331570 hasConcept C154945302 @default.
- W3009331570 hasConcept C201995342 @default.
- W3009331570 hasConcept C2776291640 @default.
- W3009331570 hasConcept C41008148 @default.
- W3009331570 hasConcept C96250715 @default.
- W3009331570 hasConceptScore W3009331570C119857082 @default.
- W3009331570 hasConceptScore W3009331570C127413603 @default.
- W3009331570 hasConceptScore W3009331570C154945302 @default.
- W3009331570 hasConceptScore W3009331570C201995342 @default.
- W3009331570 hasConceptScore W3009331570C2776291640 @default.
- W3009331570 hasConceptScore W3009331570C41008148 @default.
- W3009331570 hasConceptScore W3009331570C96250715 @default.
- W3009331570 hasFunder F4320337345 @default.
- W3009331570 hasIssue "2" @default.
- W3009331570 hasLocation W30093315701 @default.
- W3009331570 hasLocation W30093315702 @default.
- W3009331570 hasOpenAccess W3009331570 @default.
- W3009331570 hasPrimaryLocation W30093315701 @default.
- W3009331570 hasRelatedWork W1533960857 @default.
- W3009331570 hasRelatedWork W2005342428 @default.
- W3009331570 hasRelatedWork W2358177214 @default.
- W3009331570 hasRelatedWork W2360065077 @default.
- W3009331570 hasRelatedWork W2389082114 @default.
- W3009331570 hasRelatedWork W2403447209 @default.
- W3009331570 hasRelatedWork W2588279252 @default.
- W3009331570 hasRelatedWork W2913372582 @default.
- W3009331570 hasRelatedWork W3107474891 @default.
- W3009331570 hasRelatedWork W52965932 @default.
- W3009331570 hasVolume "5" @default.
- W3009331570 isParatext "false" @default.
- W3009331570 isRetracted "false" @default.
- W3009331570 magId "3009331570" @default.
- W3009331570 workType "article" @default.