FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285281382> ?p ?o ?g. }

• W4285281382 endingPage "251" @default.
• W4285281382 startingPage "235" @default.
• W4285281382 abstract "We propose a neural network (NN) approach that yields approximate solutions for high-dimensional optimal control (OC) problems and demonstrate its effectiveness using examples from multiagent path finding. Our approach yields control in a feedback form, where the policy function is given by an NN. In particular, we fuse the Hamilton–Jacobi–Bellman (HJB) and Pontryagin maximum principle (PMP) approaches by parameterizing the value function with an NN. Our approach enables us to obtain approximately OCs in real time without having to solve an optimization problem. Once the policy function is trained, generating a control at a given space–time location takes milliseconds; in contrast, efficient nonlinear programming methods typically perform the same task in seconds. We train the NN offline using the objective function of the control problem and penalty terms that enforce the HJB equations. Therefore, our training algorithm does not involve data generated by another algorithm. By training on a distribution of initial states, we ensure the controls’ optimality on a large portion of the state space. Our grid-free approach scales efficiently to dimensions where grids become impractical or infeasible. We apply our approach to several multiagent collision-avoidance problems in up to 150 dimensions. Furthermore, we empirically observe that the number of parameters in our approach scales linearly with the dimension of the control problem, thereby mitigating the curse of dimensionality." @default.
• W4285281382 created "2022-07-14" @default.
• W4285281382 creator A5002037883 @default.
• W4285281382 creator A5063432469 @default.
• W4285281382 creator A5069946985 @default.
• W4285281382 creator A5076591073 @default.
• W4285281382 creator A5078351138 @default.
• W4285281382 creator A5084125013 @default.
• W4285281382 date "2023-01-01" @default.
• W4285281382 modified "2023-10-16" @default.
• W4285281382 title "A Neural Network Approach for High-Dimensional Optimal Control Applied to Multiagent Path Finding" @default.
• W4285281382 cites W1494380031 @default.
• W4285281382 cites W153353184 @default.
• W4285281382 cites W187764570 @default.
• W4285281382 cites W1989407213 @default.
• W4285281382 cites W2003603599 @default.
• W4285281382 cites W2022144586 @default.
• W4285281382 cites W2082261506 @default.
• W4285281382 cites W2102488278 @default.
• W4285281382 cites W2111838834 @default.
• W4285281382 cites W2123030512 @default.
• W4285281382 cites W2124015815 @default.
• W4285281382 cites W2149464093 @default.
• W4285281382 cites W2162218551 @default.
• W4285281382 cites W2164642883 @default.
• W4285281382 cites W2166462345 @default.
• W4285281382 cites W2194775991 @default.
• W4285281382 cites W2546070262 @default.
• W4285281382 cites W2596147898 @default.
• W4285281382 cites W2608634483 @default.
• W4285281382 cites W2617807896 @default.
• W4285281382 cites W2625995436 @default.
• W4285281382 cites W2749028154 @default.
• W4285281382 cites W2787958879 @default.
• W4285281382 cites W2803629276 @default.
• W4285281382 cites W2886374915 @default.
• W4285281382 cites W2909966514 @default.
• W4285281382 cites W2946194484 @default.
• W4285281382 cites W2954093458 @default.
• W4285281382 cites W2963056268 @default.
• W4285281382 cites W2963395620 @default.
• W4285281382 cites W2963439316 @default.
• W4285281382 cites W2963800981 @default.
• W4285281382 cites W2964179106 @default.
• W4285281382 cites W2965543245 @default.
• W4285281382 cites W3012153102 @default.
• W4285281382 cites W3015470607 @default.
• W4285281382 cites W3016115703 @default.
• W4285281382 cites W3033325589 @default.
• W4285281382 cites W3037622062 @default.
• W4285281382 cites W3047683512 @default.
• W4285281382 cites W3091076647 @default.
• W4285281382 cites W3093985743 @default.
• W4285281382 cites W3102615019 @default.
• W4285281382 cites W3102824228 @default.
• W4285281382 cites W3103456419 @default.
• W4285281382 cites W3103572865 @default.
• W4285281382 cites W3122712863 @default.
• W4285281382 cites W3131580247 @default.
• W4285281382 cites W3150654747 @default.
• W4285281382 cites W3177242545 @default.
• W4285281382 cites W3180106877 @default.
• W4285281382 cites W3183269529 @default.
• W4285281382 cites W3206190169 @default.
• W4285281382 cites W4239369248 @default.
• W4285281382 cites W4285446270 @default.
• W4285281382 doi "https://doi.org/10.1109/tcst.2022.3172872" @default.
• W4285281382 hasPublicationYear "2023" @default.
• W4285281382 type Work @default.
• W4285281382 citedByCount "4" @default.
• W4285281382 countsByYear W42852813822022 @default.
• W4285281382 countsByYear W42852813822023 @default.
• W4285281382 crossrefType "journal-article" @default.
• W4285281382 hasAuthorship W4285281382A5002037883 @default.
• W4285281382 hasAuthorship W4285281382A5063432469 @default.
• W4285281382 hasAuthorship W4285281382A5069946985 @default.
• W4285281382 hasAuthorship W4285281382A5076591073 @default.
• W4285281382 hasAuthorship W4285281382A5078351138 @default.
• W4285281382 hasAuthorship W4285281382A5084125013 @default.
• W4285281382 hasBestOaLocation W42852813822 @default.
• W4285281382 hasConcept C105795698 @default.
• W4285281382 hasConcept C111030470 @default.
• W4285281382 hasConcept C126255220 @default.
• W4285281382 hasConcept C14646407 @default.
• W4285281382 hasConcept C154945302 @default.
• W4285281382 hasConcept C196978813 @default.
• W4285281382 hasConcept C202444582 @default.
• W4285281382 hasConcept C33676613 @default.
• W4285281382 hasConcept C33923547 @default.
• W4285281382 hasConcept C37404715 @default.
• W4285281382 hasConcept C41008148 @default.
• W4285281382 hasConcept C50644808 @default.
• W4285281382 hasConcept C72434380 @default.
• W4285281382 hasConcept C91575142 @default.
• W4285281382 hasConceptScore W4285281382C105795698 @default.
• W4285281382 hasConceptScore W4285281382C111030470 @default.
• W4285281382 hasConceptScore W4285281382C126255220 @default.
• W4285281382 hasConceptScore W4285281382C14646407 @default.

• next