Matches in SemOpenAlex for { <https://semopenalex.org/work/W3047479662> ?p ?o ?g. }
- W3047479662 abstract "Robots can learn to do complex tasks in simulation, but often, learned behaviors fail to transfer well to the real world due to simulator imperfections (the reality gap). Some existing solutions to this sim-to-real problem, such as Grounded Action Transformation (GAT), use a small amount of real-world experience to minimize the reality gap by grounding the simulator. While very effective in certain scenarios, GAT is not robust on problems that use complex function approximation techniques to model a policy. In this paper, we introduce Reinforced Grounded Action Transformation(RGAT), a new sim-to-real technique that uses Reinforcement Learning (RL) not only to update the target policy in simulation, but also to perform the grounding step itself. This novel formulation allows for end-to-end training during the grounding step, which, compared to GAT, produces a better grounded simulator. Moreover, we show experimentally in several MuJoCo domains that our approach leads to successful transfer for policies modeled using neural networks." @default.
- W3047479662 created "2020-08-10" @default.
- W3047479662 creator A5001594330 @default.
- W3047479662 creator A5008014974 @default.
- W3047479662 creator A5039434686 @default.
- W3047479662 creator A5060981901 @default.
- W3047479662 creator A5064607290 @default.
- W3047479662 date "2020-08-04" @default.
- W3047479662 modified "2023-10-01" @default.
- W3047479662 title "Reinforced Grounded Action Transformation for Sim-to-Real Transfer" @default.
- W3047479662 cites W1481659984 @default.
- W3047479662 cites W2105143952 @default.
- W3047479662 cites W2121863487 @default.
- W3047479662 cites W2595845486 @default.
- W3047479662 cites W2736601468 @default.
- W3047479662 cites W2737821837 @default.
- W3047479662 cites W2766447205 @default.
- W3047479662 cites W2899460553 @default.
- W3047479662 cites W2949608212 @default.
- W3047479662 cites W2951775809 @default.
- W3047479662 cites W2952765942 @default.
- W3047479662 cites W2963184939 @default.
- W3047479662 cites W2981030070 @default.
- W3047479662 cites W3029529904 @default.
- W3047479662 cites W3037207827 @default.
- W3047479662 cites W3047060069 @default.
- W3047479662 cites W3101442004 @default.
- W3047479662 cites W3132357684 @default.
- W3047479662 hasPublicationYear "2020" @default.
- W3047479662 type Work @default.
- W3047479662 sameAs 3047479662 @default.
- W3047479662 citedByCount "1" @default.
- W3047479662 countsByYear W30474796622020 @default.
- W3047479662 crossrefType "posted-content" @default.
- W3047479662 hasAuthorship W3047479662A5001594330 @default.
- W3047479662 hasAuthorship W3047479662A5008014974 @default.
- W3047479662 hasAuthorship W3047479662A5039434686 @default.
- W3047479662 hasAuthorship W3047479662A5060981901 @default.
- W3047479662 hasAuthorship W3047479662A5064607290 @default.
- W3047479662 hasConcept C104317684 @default.
- W3047479662 hasConcept C119599485 @default.
- W3047479662 hasConcept C121332964 @default.
- W3047479662 hasConcept C127413603 @default.
- W3047479662 hasConcept C14036430 @default.
- W3047479662 hasConcept C144024400 @default.
- W3047479662 hasConcept C150899416 @default.
- W3047479662 hasConcept C154945302 @default.
- W3047479662 hasConcept C156325361 @default.
- W3047479662 hasConcept C168993435 @default.
- W3047479662 hasConcept C173608175 @default.
- W3047479662 hasConcept C185592680 @default.
- W3047479662 hasConcept C190248442 @default.
- W3047479662 hasConcept C204241405 @default.
- W3047479662 hasConcept C2776175482 @default.
- W3047479662 hasConcept C2780791683 @default.
- W3047479662 hasConcept C36289849 @default.
- W3047479662 hasConcept C41008148 @default.
- W3047479662 hasConcept C55493867 @default.
- W3047479662 hasConcept C62520636 @default.
- W3047479662 hasConcept C78458016 @default.
- W3047479662 hasConcept C81299745 @default.
- W3047479662 hasConcept C86803240 @default.
- W3047479662 hasConcept C90509273 @default.
- W3047479662 hasConcept C97541855 @default.
- W3047479662 hasConceptScore W3047479662C104317684 @default.
- W3047479662 hasConceptScore W3047479662C119599485 @default.
- W3047479662 hasConceptScore W3047479662C121332964 @default.
- W3047479662 hasConceptScore W3047479662C127413603 @default.
- W3047479662 hasConceptScore W3047479662C14036430 @default.
- W3047479662 hasConceptScore W3047479662C144024400 @default.
- W3047479662 hasConceptScore W3047479662C150899416 @default.
- W3047479662 hasConceptScore W3047479662C154945302 @default.
- W3047479662 hasConceptScore W3047479662C156325361 @default.
- W3047479662 hasConceptScore W3047479662C168993435 @default.
- W3047479662 hasConceptScore W3047479662C173608175 @default.
- W3047479662 hasConceptScore W3047479662C185592680 @default.
- W3047479662 hasConceptScore W3047479662C190248442 @default.
- W3047479662 hasConceptScore W3047479662C204241405 @default.
- W3047479662 hasConceptScore W3047479662C2776175482 @default.
- W3047479662 hasConceptScore W3047479662C2780791683 @default.
- W3047479662 hasConceptScore W3047479662C36289849 @default.
- W3047479662 hasConceptScore W3047479662C41008148 @default.
- W3047479662 hasConceptScore W3047479662C55493867 @default.
- W3047479662 hasConceptScore W3047479662C62520636 @default.
- W3047479662 hasConceptScore W3047479662C78458016 @default.
- W3047479662 hasConceptScore W3047479662C81299745 @default.
- W3047479662 hasConceptScore W3047479662C86803240 @default.
- W3047479662 hasConceptScore W3047479662C90509273 @default.
- W3047479662 hasConceptScore W3047479662C97541855 @default.
- W3047479662 hasLocation W30474796621 @default.
- W3047479662 hasOpenAccess W3047479662 @default.
- W3047479662 hasPrimaryLocation W30474796621 @default.
- W3047479662 hasRelatedWork W2201750637 @default.
- W3047479662 hasRelatedWork W2623289472 @default.
- W3047479662 hasRelatedWork W2918049070 @default.
- W3047479662 hasRelatedWork W2922299896 @default.
- W3047479662 hasRelatedWork W2964281972 @default.
- W3047479662 hasRelatedWork W2985871261 @default.
- W3047479662 hasRelatedWork W2996793228 @default.
- W3047479662 hasRelatedWork W3033512869 @default.