FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2972586385> ?p ?o ?g. }

• W2972586385 abstract "Learning optimal feedback control laws capable of executing optimal trajectories is essential for many robotic applications. Such policies can be learned using reinforcement learning or planned using optimal control. While reinforcement learning is sample inefficient, optimal control only plans an optimal trajectory from a specific starting configuration. In this paper we propose deep optimal feedback control to learn an optimal feedback policy rather than a single trajectory. By exploiting the inherent structure of the robot dynamics and strictly convex action cost, we can derive principled cost functions such that the optimal policy naturally obeys the action limits, is globally optimal and stable on the training domain given the optimal value function. The corresponding optimal value function is learned end-to-end by embedding a deep differential network in the Hamilton-Jacobi-Bellmann differential equation and minimizing the error of this equality while simultaneously decreasing the discounting from short- to far-sighted to enable the learning. Our proposed approach enables us to learn an optimal feedback control law in continuous time, that in contrast to existing approaches generates an optimal trajectory from any point in state-space without the need of replanning. The resulting approach is evaluated on non-linear systems and achieves optimal feedback control, where standard optimal control methods require frequent replanning." @default.
• W2972586385 created "2019-09-19" @default.
• W2972586385 creator A5042151011 @default.
• W2972586385 creator A5043571353 @default.
• W2972586385 creator A5055577582 @default.
• W2972586385 creator A5071367253 @default.
• W2972586385 creator A5088706700 @default.
• W2972586385 date "2019-09-13" @default.
• W2972586385 modified "2023-09-27" @default.
• W2972586385 title "HJB Optimal Feedback Control with Deep Differential Value Functions and Action Constraints" @default.
• W2972586385 cites W1558902221 @default.
• W2972586385 cites W1578936488 @default.
• W2972586385 cites W1580348315 @default.
• W2972586385 cites W166862392 @default.
• W2972586385 cites W1964946446 @default.
• W2972586385 cites W1977237536 @default.
• W2972586385 cites W1980801308 @default.
• W2972586385 cites W1989855774 @default.
• W2972586385 cites W2042408133 @default.
• W2972586385 cites W2088986191 @default.
• W2972586385 cites W2104733512 @default.
• W2972586385 cites W2108286682 @default.
• W2972586385 cites W2113501460 @default.
• W2972586385 cites W2161697934 @default.
• W2972586385 cites W2167940675 @default.
• W2972586385 cites W2296073425 @default.
• W2972586385 cites W2296319761 @default.
• W2972586385 cites W2726187156 @default.
• W2972586385 cites W2745110207 @default.
• W2972586385 cites W2805883505 @default.
• W2972586385 cites W2842089854 @default.
• W2972586385 cites W287592399 @default.
• W2972586385 cites W2962730452 @default.
• W2972586385 cites W2990747716 @default.
• W2972586385 cites W3004137006 @default.
• W2972586385 hasPublicationYear "2019" @default.
• W2972586385 type Work @default.
• W2972586385 sameAs 2972586385 @default.
• W2972586385 citedByCount "0" @default.
• W2972586385 crossrefType "posted-content" @default.
• W2972586385 hasAuthorship W2972586385A5042151011 @default.
• W2972586385 hasAuthorship W2972586385A5043571353 @default.
• W2972586385 hasAuthorship W2972586385A5055577582 @default.
• W2972586385 hasAuthorship W2972586385A5071367253 @default.
• W2972586385 hasAuthorship W2972586385A5088706700 @default.
• W2972586385 hasConcept C121332964 @default.
• W2972586385 hasConcept C126255220 @default.
• W2972586385 hasConcept C127413603 @default.
• W2972586385 hasConcept C1276947 @default.
• W2972586385 hasConcept C13662910 @default.
• W2972586385 hasConcept C14036430 @default.
• W2972586385 hasConcept C14646407 @default.
• W2972586385 hasConcept C146978453 @default.
• W2972586385 hasConcept C154945302 @default.
• W2972586385 hasConcept C196978813 @default.
• W2972586385 hasConcept C2775924081 @default.
• W2972586385 hasConcept C2780791683 @default.
• W2972586385 hasConcept C33923547 @default.
• W2972586385 hasConcept C41008148 @default.
• W2972586385 hasConcept C41608201 @default.
• W2972586385 hasConcept C47446073 @default.
• W2972586385 hasConcept C62520636 @default.
• W2972586385 hasConcept C78458016 @default.
• W2972586385 hasConcept C86803240 @default.
• W2972586385 hasConcept C91575142 @default.
• W2972586385 hasConcept C93226319 @default.
• W2972586385 hasConcept C97541855 @default.
• W2972586385 hasConceptScore W2972586385C121332964 @default.
• W2972586385 hasConceptScore W2972586385C126255220 @default.
• W2972586385 hasConceptScore W2972586385C127413603 @default.
• W2972586385 hasConceptScore W2972586385C1276947 @default.
• W2972586385 hasConceptScore W2972586385C13662910 @default.
• W2972586385 hasConceptScore W2972586385C14036430 @default.
• W2972586385 hasConceptScore W2972586385C14646407 @default.
• W2972586385 hasConceptScore W2972586385C146978453 @default.
• W2972586385 hasConceptScore W2972586385C154945302 @default.
• W2972586385 hasConceptScore W2972586385C196978813 @default.
• W2972586385 hasConceptScore W2972586385C2775924081 @default.
• W2972586385 hasConceptScore W2972586385C2780791683 @default.
• W2972586385 hasConceptScore W2972586385C33923547 @default.
• W2972586385 hasConceptScore W2972586385C41008148 @default.
• W2972586385 hasConceptScore W2972586385C41608201 @default.
• W2972586385 hasConceptScore W2972586385C47446073 @default.
• W2972586385 hasConceptScore W2972586385C62520636 @default.
• W2972586385 hasConceptScore W2972586385C78458016 @default.
• W2972586385 hasConceptScore W2972586385C86803240 @default.
• W2972586385 hasConceptScore W2972586385C91575142 @default.
• W2972586385 hasConceptScore W2972586385C93226319 @default.
• W2972586385 hasConceptScore W2972586385C97541855 @default.
• W2972586385 hasLocation W29725863851 @default.
• W2972586385 hasOpenAccess W2972586385 @default.
• W2972586385 hasPrimaryLocation W29725863851 @default.
• W2972586385 hasRelatedWork W1801976851 @default.
• W2972586385 hasRelatedWork W1962049848 @default.
• W2972586385 hasRelatedWork W2046211166 @default.
• W2972586385 hasRelatedWork W2103541323 @default.
• W2972586385 hasRelatedWork W2118237541 @default.
• W2972586385 hasRelatedWork W2289655975 @default.
• W2972586385 hasRelatedWork W2468861737 @default.
• W2972586385 hasRelatedWork W2549367060 @default.

• next