FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3149091143> ?p ?o ?g. }

• W3149091143 abstract "We propose a neural network approach for solving high-dimensional optimal control problems arising in real-time applications. Our approach yields controls in a feedback form and can therefore handle uncertainties such as perturbations to the system's state. We accomplish this by fusing the Pontryagin Maximum Principle (PMP) and Hamilton-Jacobi-Bellman (HJB) approaches and parameterizing the value function with a neural network. We train our neural network model 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 demonstrate the effectiveness of our approach on several multi-agent 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.
• W3149091143 created "2021-04-13" @default.
• W3149091143 creator A5002037883 @default.
• W3149091143 creator A5063432469 @default.
• W3149091143 creator A5069946985 @default.
• W3149091143 creator A5076591073 @default.
• W3149091143 creator A5078351138 @default.
• W3149091143 creator A5084125013 @default.
• W3149091143 date "2021-04-07" @default.
• W3149091143 modified "2023-09-27" @default.
• W3149091143 title "A Neural Network Approach for High-Dimensional Optimal Control" @default.
• W3149091143 cites W153353184 @default.
• W3149091143 cites W187764570 @default.
• W3149091143 cites W1989407213 @default.
• W3149091143 cites W2106816694 @default.
• W3149091143 cites W2111838834 @default.
• W3149091143 cites W2123030512 @default.
• W3149091143 cites W2124015815 @default.
• W3149091143 cites W2149464093 @default.
• W3149091143 cites W2166462345 @default.
• W3149091143 cites W2194775991 @default.
• W3149091143 cites W2327668930 @default.
• W3149091143 cites W2341171179 @default.
• W3149091143 cites W2399153727 @default.
• W3149091143 cites W2551937961 @default.
• W3149091143 cites W2574186214 @default.
• W3149091143 cites W2596147898 @default.
• W3149091143 cites W2608634483 @default.
• W3149091143 cites W2617807896 @default.
• W3149091143 cites W2749408143 @default.
• W3149091143 cites W2787958879 @default.
• W3149091143 cites W2803629276 @default.
• W3149091143 cites W2886374915 @default.
• W3149091143 cites W2930930439 @default.
• W3149091143 cites W2946194484 @default.
• W3149091143 cites W2949992533 @default.
• W3149091143 cites W2954093458 @default.
• W3149091143 cites W2963056268 @default.
• W3149091143 cites W2963395620 @default.
• W3149091143 cites W2963439316 @default.
• W3149091143 cites W2963800981 @default.
• W3149091143 cites W2964121744 @default.
• W3149091143 cites W2964179106 @default.
• W3149091143 cites W2965543245 @default.
• W3149091143 cites W2982505838 @default.
• W3149091143 cites W2990553231 @default.
• W3149091143 cites W3007639617 @default.
• W3149091143 cites W3008286876 @default.
• W3149091143 cites W3016115703 @default.
• W3149091143 cites W3021722416 @default.
• W3149091143 cites W3025010137 @default.
• W3149091143 cites W3029645440 @default.
• W3149091143 cites W3030102576 @default.
• W3149091143 cites W3030175037 @default.
• W3149091143 cites W3033325589 @default.
• W3149091143 cites W3037622062 @default.
• W3149091143 cites W3047683512 @default.
• W3149091143 cites W3093985743 @default.
• W3149091143 cites W3094623068 @default.
• W3149091143 cites W3102615019 @default.
• W3149091143 cites W3102824228 @default.
• W3149091143 cites W3103456419 @default.
• W3149091143 cites W3103572865 @default.
• W3149091143 cites W3104702213 @default.
• W3149091143 cites W964554611 @default.
• W3149091143 hasPublicationYear "2021" @default.
• W3149091143 type Work @default.
• W3149091143 sameAs 3149091143 @default.
• W3149091143 citedByCount "3" @default.
• W3149091143 countsByYear W31490911432021 @default.
• W3149091143 countsByYear W31490911432022 @default.
• W3149091143 crossrefType "posted-content" @default.
• W3149091143 hasAuthorship W3149091143A5002037883 @default.
• W3149091143 hasAuthorship W3149091143A5063432469 @default.
• W3149091143 hasAuthorship W3149091143A5069946985 @default.
• W3149091143 hasAuthorship W3149091143A5076591073 @default.
• W3149091143 hasAuthorship W3149091143A5078351138 @default.
• W3149091143 hasAuthorship W3149091143A5084125013 @default.
• W3149091143 hasConcept C105795698 @default.
• W3149091143 hasConcept C111030470 @default.
• W3149091143 hasConcept C11413529 @default.
• W3149091143 hasConcept C126255220 @default.
• W3149091143 hasConcept C14036430 @default.
• W3149091143 hasConcept C14646407 @default.
• W3149091143 hasConcept C154945302 @default.
• W3149091143 hasConcept C187691185 @default.
• W3149091143 hasConcept C196978813 @default.
• W3149091143 hasConcept C202444582 @default.
• W3149091143 hasConcept C2524010 @default.
• W3149091143 hasConcept C2775924081 @default.
• W3149091143 hasConcept C33676613 @default.
• W3149091143 hasConcept C33923547 @default.
• W3149091143 hasConcept C41008148 @default.
• W3149091143 hasConcept C48103436 @default.
• W3149091143 hasConcept C50644808 @default.
• W3149091143 hasConcept C72434380 @default.
• W3149091143 hasConcept C78458016 @default.
• W3149091143 hasConcept C86803240 @default.
• W3149091143 hasConcept C91575142 @default.
• W3149091143 hasConceptScore W3149091143C105795698 @default.

• next