FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3111013878> ?p ?o ?g. }

• W3111013878 abstract "The current dominant paradigm in sensorimotor control, whether imitation or reinforcement learning, is to train policies directly in raw action spaces such as torque, joint angle, or end-effector position. This forces the agent to make decisions individually at each timestep in training, and hence, limits the scalability to continuous, high-dimensional, and long-horizon tasks. In contrast, research in classical robotics has, for a long time, exploited dynamical systems as a policy representation to learn robot behaviors via demonstrations. These techniques, however, lack the flexibility and generalizability provided by deep learning or reinforcement learning and have remained under-explored in such settings. In this work, we begin to close this gap and embed the structure of a dynamical system into deep neural network-based policies by reparameterizing action spaces via second-order differential equations. We propose Neural Dynamic Policies (NDPs) that make predictions in trajectory distribution space as opposed to prior policy learning methods where actions represent the raw control space. The embedded structure allows end-to-end policy learning for both reinforcement and imitation learning setups. We show that NDPs outperform the prior state-of-the-art in terms of either efficiency or performance across several robotic control tasks for both imitation and reinforcement learning setups. Project video and code are available at this https URL" @default.
• W3111013878 created "2020-12-21" @default.
• W3111013878 creator A5014515988 @default.
• W3111013878 creator A5053034244 @default.
• W3111013878 creator A5066151318 @default.
• W3111013878 creator A5090307838 @default.
• W3111013878 date "2020-12-04" @default.
• W3111013878 modified "2023-10-01" @default.
• W3111013878 title "Neural Dynamic Policies for End-to-End Sensorimotor Learning." @default.
• W3111013878 cites W130216483 @default.
• W3111013878 cites W1509235676 @default.
• W3111013878 cites W1594783240 @default.
• W3111013878 cites W1974849157 @default.
• W3111013878 cites W2008491851 @default.
• W3111013878 cites W2012204020 @default.
• W3111013878 cites W2012587148 @default.
• W3111013878 cites W2016765487 @default.
• W3111013878 cites W2018705428 @default.
• W3111013878 cites W2026157703 @default.
• W3111013878 cites W2060914855 @default.
• W3111013878 cites W2100993276 @default.
• W3111013878 cites W2109910161 @default.
• W3111013878 cites W2110304639 @default.
• W3111013878 cites W2111967991 @default.
• W3111013878 cites W2116226448 @default.
• W3111013878 cites W2117629901 @default.
• W3111013878 cites W2123967136 @default.
• W3111013878 cites W2136719407 @default.
• W3111013878 cites W2140135625 @default.
• W3111013878 cites W2158782408 @default.
• W3111013878 cites W2161395589 @default.
• W3111013878 cites W2161872510 @default.
• W3111013878 cites W2172158418 @default.
• W3111013878 cites W2213381658 @default.
• W3111013878 cites W2478063815 @default.
• W3111013878 cites W2736601468 @default.
• W3111013878 cites W2738231311 @default.
• W3111013878 cites W2768578623 @default.
• W3111013878 cites W2771925564 @default.
• W3111013878 cites W2783192199 @default.
• W3111013878 cites W2805762288 @default.
• W3111013878 cites W2890486280 @default.
• W3111013878 cites W2963414638 @default.
• W3111013878 cites W2963755523 @default.
• W3111013878 cites W2963970238 @default.
• W3111013878 cites W2964227312 @default.
• W3111013878 cites W2964319110 @default.
• W3111013878 cites W2969520741 @default.
• W3111013878 cites W2971162686 @default.
• W3111013878 cites W2981344907 @default.
• W3111013878 cites W3003629310 @default.
• W3111013878 cites W3009150298 @default.
• W3111013878 cites W3012294986 @default.
• W3111013878 cites W3012384939 @default.
• W3111013878 cites W3029926839 @default.
• W3111013878 cites W3104681832 @default.
• W3111013878 cites W57077127 @default.
• W3111013878 hasPublicationYear "2020" @default.
• W3111013878 type Work @default.
• W3111013878 sameAs 3111013878 @default.
• W3111013878 citedByCount "3" @default.
• W3111013878 countsByYear W31110138782021 @default.
• W3111013878 crossrefType "posted-content" @default.
• W3111013878 hasAuthorship W3111013878A5014515988 @default.
• W3111013878 hasAuthorship W3111013878A5053034244 @default.
• W3111013878 hasAuthorship W3111013878A5066151318 @default.
• W3111013878 hasAuthorship W3111013878A5090307838 @default.
• W3111013878 hasConcept C105795698 @default.
• W3111013878 hasConcept C108583219 @default.
• W3111013878 hasConcept C119857082 @default.
• W3111013878 hasConcept C121332964 @default.
• W3111013878 hasConcept C126388530 @default.
• W3111013878 hasConcept C154945302 @default.
• W3111013878 hasConcept C15744967 @default.
• W3111013878 hasConcept C2780598303 @default.
• W3111013878 hasConcept C2780791683 @default.
• W3111013878 hasConcept C33923547 @default.
• W3111013878 hasConcept C41008148 @default.
• W3111013878 hasConcept C48044578 @default.
• W3111013878 hasConcept C50644808 @default.
• W3111013878 hasConcept C62520636 @default.
• W3111013878 hasConcept C74296488 @default.
• W3111013878 hasConcept C77088390 @default.
• W3111013878 hasConcept C77805123 @default.
• W3111013878 hasConcept C97541855 @default.
• W3111013878 hasConceptScore W3111013878C105795698 @default.
• W3111013878 hasConceptScore W3111013878C108583219 @default.
• W3111013878 hasConceptScore W3111013878C119857082 @default.
• W3111013878 hasConceptScore W3111013878C121332964 @default.
• W3111013878 hasConceptScore W3111013878C126388530 @default.
• W3111013878 hasConceptScore W3111013878C154945302 @default.
• W3111013878 hasConceptScore W3111013878C15744967 @default.
• W3111013878 hasConceptScore W3111013878C2780598303 @default.
• W3111013878 hasConceptScore W3111013878C2780791683 @default.
• W3111013878 hasConceptScore W3111013878C33923547 @default.
• W3111013878 hasConceptScore W3111013878C41008148 @default.
• W3111013878 hasConceptScore W3111013878C48044578 @default.
• W3111013878 hasConceptScore W3111013878C50644808 @default.
• W3111013878 hasConceptScore W3111013878C62520636 @default.
• W3111013878 hasConceptScore W3111013878C74296488 @default.

• next