Matches in SemOpenAlex for { <https://semopenalex.org/work/W2968340082> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2968340082 abstract "Dexterous multi-fingered robotic hands can perform a wide range of manipulation skills, making them an appealing component for general-purpose robotic manipulators. However, such hands pose a major challenge for autonomous control, due to the high dimensionality of their configuration space and complex intermittent contact interactions. In this work, we propose deep reinforcement learning (deep RL) as a scalable solution for learning complex, contact rich behaviors with multi-fingered hands. Deep RL provides an end-to-end approach to directly map sensor readings to actions, without the need for task specific models or policy classes. We show that contact-rich manipulation behavior with multi-fingered hands can be learned by directly training with model-free deep RL algorithms in the real world, with minimal additional assumption and without the aid of simulation. We learn to perform a variety of tasks on two different low-cost hardware platforms entirely from scratch, and further study how the learning can be accelerated by using a small number of human demonstrations. Our experiments demonstrate that complex multi-fingered manipulation skills can be learned in the real world in about 4-7 hours for most tasks, and that demonstrations can decrease this to 2-3 hours, indicating that direct deep RL training in the real world is a viable and practical alternative to simulation and model-based control. https:// sites.google.com/view/deeprl-handmanipulation." @default.
- W2968340082 created "2019-08-22" @default.
- W2968340082 creator A5009899534 @default.
- W2968340082 creator A5017906439 @default.
- W2968340082 creator A5026322200 @default.
- W2968340082 creator A5027007388 @default.
- W2968340082 creator A5040732794 @default.
- W2968340082 date "2019-05-01" @default.
- W2968340082 modified "2023-10-10" @default.
- W2968340082 title "Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost" @default.
- W2968340082 cites W1510186039 @default.
- W2968340082 cites W1564897360 @default.
- W2968340082 cites W1820657498 @default.
- W2968340082 cites W2019165997 @default.
- W2968340082 cites W2052863493 @default.
- W2968340082 cites W2073408938 @default.
- W2968340082 cites W2112036576 @default.
- W2968340082 cites W2122331303 @default.
- W2968340082 cites W2152247404 @default.
- W2968340082 cites W2210408922 @default.
- W2968340082 cites W2416041116 @default.
- W2968340082 cites W2963170432 @default.
- W2968340082 cites W2963713397 @default.
- W2968340082 doi "https://doi.org/10.1109/icra.2019.8794102" @default.
- W2968340082 hasPublicationYear "2019" @default.
- W2968340082 type Work @default.
- W2968340082 sameAs 2968340082 @default.
- W2968340082 citedByCount "97" @default.
- W2968340082 countsByYear W29683400822019 @default.
- W2968340082 countsByYear W29683400822020 @default.
- W2968340082 countsByYear W29683400822021 @default.
- W2968340082 countsByYear W29683400822022 @default.
- W2968340082 countsByYear W29683400822023 @default.
- W2968340082 crossrefType "proceedings-article" @default.
- W2968340082 hasAuthorship W2968340082A5009899534 @default.
- W2968340082 hasAuthorship W2968340082A5017906439 @default.
- W2968340082 hasAuthorship W2968340082A5026322200 @default.
- W2968340082 hasAuthorship W2968340082A5027007388 @default.
- W2968340082 hasAuthorship W2968340082A5040732794 @default.
- W2968340082 hasBestOaLocation W29683400822 @default.
- W2968340082 hasConcept C107457646 @default.
- W2968340082 hasConcept C108583219 @default.
- W2968340082 hasConcept C111030470 @default.
- W2968340082 hasConcept C111919701 @default.
- W2968340082 hasConcept C121332964 @default.
- W2968340082 hasConcept C127413603 @default.
- W2968340082 hasConcept C154945302 @default.
- W2968340082 hasConcept C168167062 @default.
- W2968340082 hasConcept C201995342 @default.
- W2968340082 hasConcept C2780451532 @default.
- W2968340082 hasConcept C2781235140 @default.
- W2968340082 hasConcept C41008148 @default.
- W2968340082 hasConcept C48044578 @default.
- W2968340082 hasConcept C77088390 @default.
- W2968340082 hasConcept C97355855 @default.
- W2968340082 hasConcept C97541855 @default.
- W2968340082 hasConceptScore W2968340082C107457646 @default.
- W2968340082 hasConceptScore W2968340082C108583219 @default.
- W2968340082 hasConceptScore W2968340082C111030470 @default.
- W2968340082 hasConceptScore W2968340082C111919701 @default.
- W2968340082 hasConceptScore W2968340082C121332964 @default.
- W2968340082 hasConceptScore W2968340082C127413603 @default.
- W2968340082 hasConceptScore W2968340082C154945302 @default.
- W2968340082 hasConceptScore W2968340082C168167062 @default.
- W2968340082 hasConceptScore W2968340082C201995342 @default.
- W2968340082 hasConceptScore W2968340082C2780451532 @default.
- W2968340082 hasConceptScore W2968340082C2781235140 @default.
- W2968340082 hasConceptScore W2968340082C41008148 @default.
- W2968340082 hasConceptScore W2968340082C48044578 @default.
- W2968340082 hasConceptScore W2968340082C77088390 @default.
- W2968340082 hasConceptScore W2968340082C97355855 @default.
- W2968340082 hasConceptScore W2968340082C97541855 @default.
- W2968340082 hasLocation W29683400821 @default.
- W2968340082 hasLocation W29683400822 @default.
- W2968340082 hasOpenAccess W2968340082 @default.
- W2968340082 hasPrimaryLocation W29683400821 @default.
- W2968340082 hasRelatedWork W1525643724 @default.
- W2968340082 hasRelatedWork W2065109233 @default.
- W2968340082 hasRelatedWork W2067938758 @default.
- W2968340082 hasRelatedWork W2364921833 @default.
- W2968340082 hasRelatedWork W2731899572 @default.
- W2968340082 hasRelatedWork W3037422413 @default.
- W2968340082 hasRelatedWork W3209969885 @default.
- W2968340082 hasRelatedWork W4206669594 @default.
- W2968340082 hasRelatedWork W4285805438 @default.
- W2968340082 hasRelatedWork W4294811414 @default.
- W2968340082 isParatext "false" @default.
- W2968340082 isRetracted "false" @default.
- W2968340082 magId "2968340082" @default.
- W2968340082 workType "article" @default.