Matches in SemOpenAlex for { <https://semopenalex.org/work/W3029831493> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3029831493 endingPage "869" @default.
- W3029831493 startingPage "854" @default.
- W3029831493 abstract "Humans and animals are capable of quickly learning new behaviours to solve new tasks. Yet, we often forget that they also rely on a highly specialized morphology that co-adapted with motor control throughout thousands of years. Although compelling, the idea of co-adapting morphology and behaviours in robots is often unfeasible because of the long manufacturing times, and the need to re-design an appropriate controller for each morphology. In this paper, we propose a novel approach to automatically and efficiently co-adapt a robot morphology and its controller. Our approach is based on recent advances in deep reinforcement learning, and specifically the soft actor critic algorithm. Key to our approach is the possibility of leveraging previously tested morphologies and behaviors to estimate the performance of new candidate morphologies. As such, we can make full use of the information available for making more informed decisions, with the ultimate goal of achieving a more data-efficient co-adaptation (i.e., reducing the number of morphologies and behaviors tested). Simulated experiments show that our approach requires drastically less design prototypes to find good morphology-behaviour combinations, making this method particularly suitable for future co-adaptation of robot designs in the real world." @default.
- W3029831493 created "2020-06-05" @default.
- W3029831493 creator A5002235575 @default.
- W3029831493 creator A5024068845 @default.
- W3029831493 creator A5040226194 @default.
- W3029831493 date "2019-01-01" @default.
- W3029831493 modified "2023-09-26" @default.
- W3029831493 title "Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning" @default.
- W3029831493 hasPublicationYear "2019" @default.
- W3029831493 type Work @default.
- W3029831493 sameAs 3029831493 @default.
- W3029831493 citedByCount "11" @default.
- W3029831493 countsByYear W30298314932020 @default.
- W3029831493 countsByYear W30298314932021 @default.
- W3029831493 countsByYear W30298314932023 @default.
- W3029831493 crossrefType "journal-article" @default.
- W3029831493 hasAuthorship W3029831493A5002235575 @default.
- W3029831493 hasAuthorship W3029831493A5024068845 @default.
- W3029831493 hasAuthorship W3029831493A5040226194 @default.
- W3029831493 hasConcept C107457646 @default.
- W3029831493 hasConcept C119857082 @default.
- W3029831493 hasConcept C120665830 @default.
- W3029831493 hasConcept C121332964 @default.
- W3029831493 hasConcept C139807058 @default.
- W3029831493 hasConcept C154945302 @default.
- W3029831493 hasConcept C203479927 @default.
- W3029831493 hasConcept C26517878 @default.
- W3029831493 hasConcept C38652104 @default.
- W3029831493 hasConcept C41008148 @default.
- W3029831493 hasConcept C6557445 @default.
- W3029831493 hasConcept C86803240 @default.
- W3029831493 hasConcept C90509273 @default.
- W3029831493 hasConcept C97541855 @default.
- W3029831493 hasConceptScore W3029831493C107457646 @default.
- W3029831493 hasConceptScore W3029831493C119857082 @default.
- W3029831493 hasConceptScore W3029831493C120665830 @default.
- W3029831493 hasConceptScore W3029831493C121332964 @default.
- W3029831493 hasConceptScore W3029831493C139807058 @default.
- W3029831493 hasConceptScore W3029831493C154945302 @default.
- W3029831493 hasConceptScore W3029831493C203479927 @default.
- W3029831493 hasConceptScore W3029831493C26517878 @default.
- W3029831493 hasConceptScore W3029831493C38652104 @default.
- W3029831493 hasConceptScore W3029831493C41008148 @default.
- W3029831493 hasConceptScore W3029831493C6557445 @default.
- W3029831493 hasConceptScore W3029831493C86803240 @default.
- W3029831493 hasConceptScore W3029831493C90509273 @default.
- W3029831493 hasConceptScore W3029831493C97541855 @default.
- W3029831493 hasLocation W30298314931 @default.
- W3029831493 hasOpenAccess W3029831493 @default.
- W3029831493 hasPrimaryLocation W30298314931 @default.
- W3029831493 hasRelatedWork W1609223620 @default.
- W3029831493 hasRelatedWork W2117085697 @default.
- W3029831493 hasRelatedWork W2127197749 @default.
- W3029831493 hasRelatedWork W2158782408 @default.
- W3029831493 hasRelatedWork W2701942770 @default.
- W3029831493 hasRelatedWork W2736021157 @default.
- W3029831493 hasRelatedWork W2736601468 @default.
- W3029831493 hasRelatedWork W2785948534 @default.
- W3029831493 hasRelatedWork W2794757725 @default.
- W3029831493 hasRelatedWork W2807229064 @default.
- W3029831493 hasRelatedWork W2909770505 @default.
- W3029831493 hasRelatedWork W2962696179 @default.
- W3029831493 hasRelatedWork W2967894826 @default.
- W3029831493 hasRelatedWork W2968042644 @default.
- W3029831493 hasRelatedWork W2970292059 @default.
- W3029831493 hasRelatedWork W2970293125 @default.
- W3029831493 hasRelatedWork W3048943668 @default.
- W3029831493 hasRelatedWork W3106528330 @default.
- W3029831493 hasRelatedWork W3115727409 @default.
- W3029831493 hasRelatedWork W3130877679 @default.
- W3029831493 isParatext "false" @default.
- W3029831493 isRetracted "false" @default.
- W3029831493 magId "3029831493" @default.
- W3029831493 workType "article" @default.