Matches in SemOpenAlex for { <https://semopenalex.org/work/W3095412669> ?p ?o ?g. }
- W3095412669 abstract "Reinforcement Learning (RL) of robotic manipulation skills, despite its impressive successes, stands to benefit from incorporating domain knowledge from control theory. One of the most important properties that is of interest is control stability. Ideally, one would like to achieve stability guarantees while staying within the framework of state-of-the-art deep RL algorithms. Such a solution does not exist in general, especially one that scales to complex manipulation tasks. We contribute towards closing this gap by introducing $textit{normalizing-flow}$ control structure, that can be deployed in any latest deep RL algorithms. While stable exploration is not guaranteed, our method is designed to ultimately produce deterministic controllers with provable stability. In addition to demonstrating our method on challenging contact-rich manipulation tasks, we also show that it is possible to achieve considerable exploration efficiency--reduced state space coverage and actuation efforts--without losing learning efficiency." @default.
- W3095412669 created "2020-11-09" @default.
- W3095412669 creator A5023792180 @default.
- W3095412669 creator A5052271324 @default.
- W3095412669 creator A5067144254 @default.
- W3095412669 creator A5076700669 @default.
- W3095412669 date "2020-10-30" @default.
- W3095412669 modified "2023-10-03" @default.
- W3095412669 title "Learning Stable Normalizing-Flow Control for Robotic Manipulation" @default.
- W3095412669 cites W1487127700 @default.
- W3095412669 cites W1560270123 @default.
- W3095412669 cites W1925816294 @default.
- W3095412669 cites W1974357213 @default.
- W3095412669 cites W2091946780 @default.
- W3095412669 cites W2098524868 @default.
- W3095412669 cites W2106871887 @default.
- W3095412669 cites W2112535044 @default.
- W3095412669 cites W2126909264 @default.
- W3095412669 cites W2164479831 @default.
- W3095412669 cites W2296438681 @default.
- W3095412669 cites W2497095191 @default.
- W3095412669 cites W2618318883 @default.
- W3095412669 cites W2736601468 @default.
- W3095412669 cites W2946396478 @default.
- W3095412669 cites W2962695743 @default.
- W3095412669 cites W2962736495 @default.
- W3095412669 cites W2964161785 @default.
- W3095412669 cites W2966735560 @default.
- W3095412669 cites W2968095426 @default.
- W3095412669 cites W2992005611 @default.
- W3095412669 cites W3003629310 @default.
- W3095412669 cites W3044718039 @default.
- W3095412669 cites W3091037773 @default.
- W3095412669 cites W3106892592 @default.
- W3095412669 hasPublicationYear "2020" @default.
- W3095412669 type Work @default.
- W3095412669 sameAs 3095412669 @default.
- W3095412669 citedByCount "1" @default.
- W3095412669 countsByYear W30954126692021 @default.
- W3095412669 crossrefType "posted-content" @default.
- W3095412669 hasAuthorship W3095412669A5023792180 @default.
- W3095412669 hasAuthorship W3095412669A5052271324 @default.
- W3095412669 hasAuthorship W3095412669A5067144254 @default.
- W3095412669 hasAuthorship W3095412669A5076700669 @default.
- W3095412669 hasConcept C105795698 @default.
- W3095412669 hasConcept C111919701 @default.
- W3095412669 hasConcept C112972136 @default.
- W3095412669 hasConcept C11413529 @default.
- W3095412669 hasConcept C119857082 @default.
- W3095412669 hasConcept C127413603 @default.
- W3095412669 hasConcept C133731056 @default.
- W3095412669 hasConcept C134306372 @default.
- W3095412669 hasConcept C154945302 @default.
- W3095412669 hasConcept C17744445 @default.
- W3095412669 hasConcept C186766456 @default.
- W3095412669 hasConcept C199539241 @default.
- W3095412669 hasConcept C2524010 @default.
- W3095412669 hasConcept C2775924081 @default.
- W3095412669 hasConcept C2778572836 @default.
- W3095412669 hasConcept C2778775528 @default.
- W3095412669 hasConcept C31258907 @default.
- W3095412669 hasConcept C33923547 @default.
- W3095412669 hasConcept C36503486 @default.
- W3095412669 hasConcept C38349280 @default.
- W3095412669 hasConcept C41008148 @default.
- W3095412669 hasConcept C47446073 @default.
- W3095412669 hasConcept C48103436 @default.
- W3095412669 hasConcept C72434380 @default.
- W3095412669 hasConcept C97541855 @default.
- W3095412669 hasConceptScore W3095412669C105795698 @default.
- W3095412669 hasConceptScore W3095412669C111919701 @default.
- W3095412669 hasConceptScore W3095412669C112972136 @default.
- W3095412669 hasConceptScore W3095412669C11413529 @default.
- W3095412669 hasConceptScore W3095412669C119857082 @default.
- W3095412669 hasConceptScore W3095412669C127413603 @default.
- W3095412669 hasConceptScore W3095412669C133731056 @default.
- W3095412669 hasConceptScore W3095412669C134306372 @default.
- W3095412669 hasConceptScore W3095412669C154945302 @default.
- W3095412669 hasConceptScore W3095412669C17744445 @default.
- W3095412669 hasConceptScore W3095412669C186766456 @default.
- W3095412669 hasConceptScore W3095412669C199539241 @default.
- W3095412669 hasConceptScore W3095412669C2524010 @default.
- W3095412669 hasConceptScore W3095412669C2775924081 @default.
- W3095412669 hasConceptScore W3095412669C2778572836 @default.
- W3095412669 hasConceptScore W3095412669C2778775528 @default.
- W3095412669 hasConceptScore W3095412669C31258907 @default.
- W3095412669 hasConceptScore W3095412669C33923547 @default.
- W3095412669 hasConceptScore W3095412669C36503486 @default.
- W3095412669 hasConceptScore W3095412669C38349280 @default.
- W3095412669 hasConceptScore W3095412669C41008148 @default.
- W3095412669 hasConceptScore W3095412669C47446073 @default.
- W3095412669 hasConceptScore W3095412669C48103436 @default.
- W3095412669 hasConceptScore W3095412669C72434380 @default.
- W3095412669 hasConceptScore W3095412669C97541855 @default.
- W3095412669 hasOpenAccess W3095412669 @default.
- W3095412669 hasRelatedWork W1863534978 @default.
- W3095412669 hasRelatedWork W190583841 @default.
- W3095412669 hasRelatedWork W2554830522 @default.
- W3095412669 hasRelatedWork W2610395436 @default.
- W3095412669 hasRelatedWork W2919334316 @default.