Matches in SemOpenAlex for { <https://semopenalex.org/work/W2905658145> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2905658145 endingPage "600" @default.
- W2905658145 startingPage "587" @default.
- W2905658145 abstract "Packet routing problem most commonly emerges in the context of computer networks, thus the majority of routing algorithms existing nowadays is designed specifically for routing in computer networks. However, in the logistics domain, many problems can be formulated in terms of packet routing, e.g. in automated traffic routing or material handling systems. In this paper, we propose an algorithm for packet routing in such heterogeneous environments. Our approach is based on deep reinforcement learning networks combined with link-state protocol and preliminary supervised learning. Similarly to most routing algorithms, the proposed algorithm is a distributed one and is designed to run on a network constructed from interconnected routers. Unlike most other algorithms, proposed one views routers as learning agents, representing the routing problem as a multi-agent reinforcement learning problem. Modeling each router as a deep neural network allows each router to account for heterogeneous data about its environment, allowing for optimization of more complex cost functions, like in case of simultaneous optimization of bag delivery time and energy consumption in a baggage handling system. We tested the algorithm using manually constructed simulation models of computer network and baggage handling system. It outperforms state-of-the-art routing algorithms." @default.
- W2905658145 created "2019-01-01" @default.
- W2905658145 creator A5000959052 @default.
- W2905658145 creator A5008070913 @default.
- W2905658145 creator A5064203398 @default.
- W2905658145 creator A5079881929 @default.
- W2905658145 date "2019-05-01" @default.
- W2905658145 modified "2023-09-27" @default.
- W2905658145 title "Multi-agent deep learning for simultaneous optimization for time and energy in distributed routing system" @default.
- W2905658145 cites W1641379095 @default.
- W2905658145 cites W1664011265 @default.
- W2905658145 cites W2000875519 @default.
- W2905658145 cites W2049416242 @default.
- W2905658145 cites W2064675550 @default.
- W2905658145 cites W2128110222 @default.
- W2905658145 cites W2145339207 @default.
- W2905658145 cites W2150519657 @default.
- W2905658145 cites W2156073109 @default.
- W2905658145 cites W2228607910 @default.
- W2905658145 cites W2599320013 @default.
- W2905658145 doi "https://doi.org/10.1016/j.future.2018.12.037" @default.
- W2905658145 hasPublicationYear "2019" @default.
- W2905658145 type Work @default.
- W2905658145 sameAs 2905658145 @default.
- W2905658145 citedByCount "24" @default.
- W2905658145 countsByYear W29056581452019 @default.
- W2905658145 countsByYear W29056581452020 @default.
- W2905658145 countsByYear W29056581452021 @default.
- W2905658145 countsByYear W29056581452022 @default.
- W2905658145 countsByYear W29056581452023 @default.
- W2905658145 crossrefType "journal-article" @default.
- W2905658145 hasAuthorship W2905658145A5000959052 @default.
- W2905658145 hasAuthorship W2905658145A5008070913 @default.
- W2905658145 hasAuthorship W2905658145A5064203398 @default.
- W2905658145 hasAuthorship W2905658145A5079881929 @default.
- W2905658145 hasBestOaLocation W29056581452 @default.
- W2905658145 hasConcept C104954878 @default.
- W2905658145 hasConcept C120314980 @default.
- W2905658145 hasConcept C154945302 @default.
- W2905658145 hasConcept C158379750 @default.
- W2905658145 hasConcept C177818476 @default.
- W2905658145 hasConcept C184896649 @default.
- W2905658145 hasConcept C196423136 @default.
- W2905658145 hasConcept C204948658 @default.
- W2905658145 hasConcept C31258907 @default.
- W2905658145 hasConcept C41008148 @default.
- W2905658145 hasConcept C74172769 @default.
- W2905658145 hasConcept C87044965 @default.
- W2905658145 hasConcept C89305328 @default.
- W2905658145 hasConcept C94600068 @default.
- W2905658145 hasConcept C9659607 @default.
- W2905658145 hasConcept C97541855 @default.
- W2905658145 hasConceptScore W2905658145C104954878 @default.
- W2905658145 hasConceptScore W2905658145C120314980 @default.
- W2905658145 hasConceptScore W2905658145C154945302 @default.
- W2905658145 hasConceptScore W2905658145C158379750 @default.
- W2905658145 hasConceptScore W2905658145C177818476 @default.
- W2905658145 hasConceptScore W2905658145C184896649 @default.
- W2905658145 hasConceptScore W2905658145C196423136 @default.
- W2905658145 hasConceptScore W2905658145C204948658 @default.
- W2905658145 hasConceptScore W2905658145C31258907 @default.
- W2905658145 hasConceptScore W2905658145C41008148 @default.
- W2905658145 hasConceptScore W2905658145C74172769 @default.
- W2905658145 hasConceptScore W2905658145C87044965 @default.
- W2905658145 hasConceptScore W2905658145C89305328 @default.
- W2905658145 hasConceptScore W2905658145C94600068 @default.
- W2905658145 hasConceptScore W2905658145C9659607 @default.
- W2905658145 hasConceptScore W2905658145C97541855 @default.
- W2905658145 hasFunder F4320321912 @default.
- W2905658145 hasLocation W29056581451 @default.
- W2905658145 hasLocation W29056581452 @default.
- W2905658145 hasOpenAccess W2905658145 @default.
- W2905658145 hasPrimaryLocation W29056581451 @default.
- W2905658145 hasRelatedWork W1585786976 @default.
- W2905658145 hasRelatedWork W1616997497 @default.
- W2905658145 hasRelatedWork W2138324936 @default.
- W2905658145 hasRelatedWork W2138861014 @default.
- W2905658145 hasRelatedWork W2220567392 @default.
- W2905658145 hasRelatedWork W2380567565 @default.
- W2905658145 hasRelatedWork W2524341991 @default.
- W2905658145 hasRelatedWork W2783971594 @default.
- W2905658145 hasRelatedWork W4323344880 @default.
- W2905658145 hasRelatedWork W2096480024 @default.
- W2905658145 hasVolume "94" @default.
- W2905658145 isParatext "false" @default.
- W2905658145 isRetracted "false" @default.
- W2905658145 magId "2905658145" @default.
- W2905658145 workType "article" @default.