Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100238596> ?p ?o ?g. }
- W3100238596 endingPage "2904" @default.
- W3100238596 startingPage "2897" @default.
- W3100238596 abstract "We present an Imitation Learning approach for the control of dynamical systems with a known model. Our policy search method is guided by solutions from Model Predictive Control (MPC). Typical policy search methods of this kind minimize a distance metric between the guiding demonstrations and the learned policy. Our loss function, however, corresponds to the minimization of the control Hamiltonian, which derives from the principle of optimality. Therefore, our algorithm directly attempts to solve the optimality conditions with a parameterized class of control laws. Additionally, the proposed loss function explicitly encodes the constraints of the optimal control problem and we provide numerical evidence that its minimization achieves improved constraint satisfaction. We train a mixture-of-expert neural network architecture for controlling a quadrupedal robot and show that this policy structure is well suited for such multimodal systems. The learned policy can successfully stabilize different gaits on the real walking robot from less than 10 min of demonstration data." @default.
- W3100238596 created "2020-11-23" @default.
- W3100238596 creator A5040208292 @default.
- W3100238596 creator A5044258783 @default.
- W3100238596 creator A5071891853 @default.
- W3100238596 date "2020-04-01" @default.
- W3100238596 modified "2023-10-18" @default.
- W3100238596 title "MPC-Net: A First Principles Guided Policy Search" @default.
- W3100238596 cites W1502718064 @default.
- W3100238596 cites W1967821692 @default.
- W3100238596 cites W2134491302 @default.
- W3100238596 cites W2141559645 @default.
- W3100238596 cites W2150884987 @default.
- W3100238596 cites W2295431040 @default.
- W3100238596 cites W2333533581 @default.
- W3100238596 cites W2618250881 @default.
- W3100238596 cites W2771691050 @default.
- W3100238596 cites W2788030459 @default.
- W3100238596 cites W2907537824 @default.
- W3100238596 cites W2911087563 @default.
- W3100238596 cites W2951805468 @default.
- W3100238596 cites W2963184939 @default.
- W3100238596 cites W2964070888 @default.
- W3100238596 cites W2970228732 @default.
- W3100238596 cites W3101780148 @default.
- W3100238596 cites W3103075896 @default.
- W3100238596 cites W3105372678 @default.
- W3100238596 cites W4300309110 @default.
- W3100238596 doi "https://doi.org/10.1109/lra.2020.2974653" @default.
- W3100238596 hasPublicationYear "2020" @default.
- W3100238596 type Work @default.
- W3100238596 sameAs 3100238596 @default.
- W3100238596 citedByCount "27" @default.
- W3100238596 countsByYear W31002385962020 @default.
- W3100238596 countsByYear W31002385962021 @default.
- W3100238596 countsByYear W31002385962022 @default.
- W3100238596 countsByYear W31002385962023 @default.
- W3100238596 crossrefType "journal-article" @default.
- W3100238596 hasAuthorship W3100238596A5040208292 @default.
- W3100238596 hasAuthorship W3100238596A5044258783 @default.
- W3100238596 hasAuthorship W3100238596A5071891853 @default.
- W3100238596 hasBestOaLocation W31002385962 @default.
- W3100238596 hasConcept C11413529 @default.
- W3100238596 hasConcept C126255220 @default.
- W3100238596 hasConcept C127413603 @default.
- W3100238596 hasConcept C14036430 @default.
- W3100238596 hasConcept C147764199 @default.
- W3100238596 hasConcept C154945302 @default.
- W3100238596 hasConcept C165464430 @default.
- W3100238596 hasConcept C172205157 @default.
- W3100238596 hasConcept C176217482 @default.
- W3100238596 hasConcept C21547014 @default.
- W3100238596 hasConcept C2775924081 @default.
- W3100238596 hasConcept C33923547 @default.
- W3100238596 hasConcept C41008148 @default.
- W3100238596 hasConcept C44616089 @default.
- W3100238596 hasConcept C47446073 @default.
- W3100238596 hasConcept C49937458 @default.
- W3100238596 hasConcept C50644808 @default.
- W3100238596 hasConcept C78458016 @default.
- W3100238596 hasConcept C86803240 @default.
- W3100238596 hasConcept C90509273 @default.
- W3100238596 hasConcept C91575142 @default.
- W3100238596 hasConceptScore W3100238596C11413529 @default.
- W3100238596 hasConceptScore W3100238596C126255220 @default.
- W3100238596 hasConceptScore W3100238596C127413603 @default.
- W3100238596 hasConceptScore W3100238596C14036430 @default.
- W3100238596 hasConceptScore W3100238596C147764199 @default.
- W3100238596 hasConceptScore W3100238596C154945302 @default.
- W3100238596 hasConceptScore W3100238596C165464430 @default.
- W3100238596 hasConceptScore W3100238596C172205157 @default.
- W3100238596 hasConceptScore W3100238596C176217482 @default.
- W3100238596 hasConceptScore W3100238596C21547014 @default.
- W3100238596 hasConceptScore W3100238596C2775924081 @default.
- W3100238596 hasConceptScore W3100238596C33923547 @default.
- W3100238596 hasConceptScore W3100238596C41008148 @default.
- W3100238596 hasConceptScore W3100238596C44616089 @default.
- W3100238596 hasConceptScore W3100238596C47446073 @default.
- W3100238596 hasConceptScore W3100238596C49937458 @default.
- W3100238596 hasConceptScore W3100238596C50644808 @default.
- W3100238596 hasConceptScore W3100238596C78458016 @default.
- W3100238596 hasConceptScore W3100238596C86803240 @default.
- W3100238596 hasConceptScore W3100238596C90509273 @default.
- W3100238596 hasConceptScore W3100238596C91575142 @default.
- W3100238596 hasIssue "2" @default.
- W3100238596 hasLocation W31002385961 @default.
- W3100238596 hasLocation W31002385962 @default.
- W3100238596 hasLocation W31002385963 @default.
- W3100238596 hasLocation W31002385964 @default.
- W3100238596 hasOpenAccess W3100238596 @default.
- W3100238596 hasPrimaryLocation W31002385961 @default.
- W3100238596 hasRelatedWork W1917046051 @default.
- W3100238596 hasRelatedWork W2014376512 @default.
- W3100238596 hasRelatedWork W2017798257 @default.
- W3100238596 hasRelatedWork W2078043032 @default.
- W3100238596 hasRelatedWork W2152136198 @default.
- W3100238596 hasRelatedWork W2357085366 @default.
- W3100238596 hasRelatedWork W2370949144 @default.