FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945975258> ?p ?o ?g. }

• W2945975258 abstract "Conservation laws are considered to be fundamental laws of nature. It has broad applications in many fields, including physics, chemistry, biology, geology, and engineering. Solving the differential equations associated with conservation laws is a major branch in computational mathematics. The recent success of machine learning, especially deep learning in areas such as computer vision and natural language processing, has attracted a lot of attention from the community of computational mathematics and inspired many intriguing works in combining machine learning with traditional methods. In this paper, we are the first to view numerical PDE solvers as an MDP and to use (deep) RL to learn new solvers. As proof of concept, we focus on 1-dimensional scalar conservation laws. We deploy the machinery of deep reinforcement learning to train a policy network that can decide on how the numerical solutions should be approximated in a sequential and spatial-temporal adaptive manner. We will show that the problem of solving conservation laws can be naturally viewed as a sequential decision-making process, and the numerical schemes learned in such a way can easily enforce long-term accuracy. Furthermore, the learned policy network is carefully designed to determine a good local discrete approximation based on the current state of the solution, which essentially makes the proposed method a meta-learning approach. In other words, the proposed method is capable of learning how to discretize for a given situation mimicking human experts. Finally, we will provide details on how the policy network is trained, how well it performs compared with some state-of-the-art numerical solvers such as WENO schemes, and supervised learning based approach L3D and PINN, and how well it generalizes." @default.
• W2945975258 created "2019-05-29" @default.
• W2945975258 creator A5035182164 @default.
• W2945975258 creator A5035683291 @default.
• W2945975258 creator A5039367145 @default.
• W2945975258 creator A5047207607 @default.
• W2945975258 date "2019-05-27" @default.
• W2945975258 modified "2023-09-23" @default.
• W2945975258 title "Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning" @default.
• W2945975258 cites W1555627060 @default.
• W2945975258 cites W1598377843 @default.
• W2945975258 cites W1976692802 @default.
• W2945975258 cites W2034976587 @default.
• W2945975258 cites W2045849310 @default.
• W2945975258 cites W2049391017 @default.
• W2945975258 cites W2145339207 @default.
• W2945975258 cites W2151693816 @default.
• W2945975258 cites W2173248099 @default.
• W2945975258 cites W2257979135 @default.
• W2945975258 cites W2409744450 @default.
• W2945975258 cites W2557283755 @default.
• W2945975258 cites W2600297185 @default.
• W2945975258 cites W2604763608 @default.
• W2945975258 cites W2736601468 @default.
• W2945975258 cites W2741183886 @default.
• W2945975258 cites W2749028154 @default.
• W2945975258 cites W2754833785 @default.
• W2945975258 cites W2760972773 @default.
• W2945975258 cites W2766207105 @default.
• W2945975258 cites W2768535327 @default.
• W2945975258 cites W2772097715 @default.
• W2945975258 cites W2787938642 @default.
• W2945975258 cites W2803629276 @default.
• W2945975258 cites W2808746463 @default.
• W2945975258 cites W2810630164 @default.
• W2945975258 cites W2884569173 @default.
• W2945975258 cites W2891039272 @default.
• W2945975258 cites W2895531857 @default.
• W2945975258 cites W2899283552 @default.
• W2945975258 cites W2903660960 @default.
• W2945975258 cites W2937653888 @default.
• W2945975258 cites W2940929008 @default.
• W2945975258 cites W2944695225 @default.
• W2945975258 cites W2944808962 @default.
• W2945975258 cites W2949608212 @default.
• W2945975258 cites W2963302407 @default.
• W2945975258 cites W2963775850 @default.
• W2945975258 cites W2964156122 @default.
• W2945975258 cites W2972859114 @default.
• W2945975258 cites W2981014499 @default.
• W2945975258 cites W3004828050 @default.
• W2945975258 cites W3098175809 @default.
• W2945975258 cites W3100626142 @default.
• W2945975258 doi "https://doi.org/10.48550/arxiv.1905.11079" @default.
• W2945975258 hasPublicationYear "2019" @default.
• W2945975258 type Work @default.
• W2945975258 sameAs 2945975258 @default.
• W2945975258 citedByCount "1" @default.
• W2945975258 countsByYear W29459752582020 @default.
• W2945975258 crossrefType "posted-content" @default.
• W2945975258 hasAuthorship W2945975258A5035182164 @default.
• W2945975258 hasAuthorship W2945975258A5035683291 @default.
• W2945975258 hasAuthorship W2945975258A5039367145 @default.
• W2945975258 hasAuthorship W2945975258A5047207607 @default.
• W2945975258 hasBestOaLocation W29459752581 @default.
• W2945975258 hasConcept C108583219 @default.
• W2945975258 hasConcept C111472728 @default.
• W2945975258 hasConcept C126255220 @default.
• W2945975258 hasConcept C134306372 @default.
• W2945975258 hasConcept C138885662 @default.
• W2945975258 hasConcept C154945302 @default.
• W2945975258 hasConcept C194583477 @default.
• W2945975258 hasConcept C2524010 @default.
• W2945975258 hasConcept C33923547 @default.
• W2945975258 hasConcept C3445786 @default.
• W2945975258 hasConcept C41008148 @default.
• W2945975258 hasConcept C57691317 @default.
• W2945975258 hasConcept C73000952 @default.
• W2945975258 hasConcept C80444323 @default.
• W2945975258 hasConcept C97541855 @default.
• W2945975258 hasConceptScore W2945975258C108583219 @default.
• W2945975258 hasConceptScore W2945975258C111472728 @default.
• W2945975258 hasConceptScore W2945975258C126255220 @default.
• W2945975258 hasConceptScore W2945975258C134306372 @default.
• W2945975258 hasConceptScore W2945975258C138885662 @default.
• W2945975258 hasConceptScore W2945975258C154945302 @default.
• W2945975258 hasConceptScore W2945975258C194583477 @default.
• W2945975258 hasConceptScore W2945975258C2524010 @default.
• W2945975258 hasConceptScore W2945975258C33923547 @default.
• W2945975258 hasConceptScore W2945975258C3445786 @default.
• W2945975258 hasConceptScore W2945975258C41008148 @default.
• W2945975258 hasConceptScore W2945975258C57691317 @default.
• W2945975258 hasConceptScore W2945975258C73000952 @default.
• W2945975258 hasConceptScore W2945975258C80444323 @default.
• W2945975258 hasConceptScore W2945975258C97541855 @default.
• W2945975258 hasLocation W29459752581 @default.
• W2945975258 hasOpenAccess W2945975258 @default.
• W2945975258 hasPrimaryLocation W29459752581 @default.
• W2945975258 hasRelatedWork W1531962215 @default.
• W2945975258 hasRelatedWork W2011918306 @default.

• next