Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385358041> ?p ?o ?g. }
- W4385358041 endingPage "409" @default.
- W4385358041 startingPage "396" @default.
- W4385358041 abstract "Tackling traffic signal control through multi-agent reinforcement learning is a widely-employed approach. However, current state-of-the-art models have drawbacks: intersections optimize their own local rewards and cause traffic to waste time and fuel with a start-stop mode at each intersection. They also lack information sharing among intersections and their specialized policy hinders the ability to adapt to new traffic scenarios. To overcome these limitations, This work presents a centralized collaborative graph network (CCGN) with the core objective of a signal-free corridor once the traffic flows have waited at the entry intersection of the traffic intersection network on either side, the subsequent intersection gives the open signal as the traffic flows arrive. CCGN combines local policy networks (LPN) and global policy networks, where LPN employed at each intersection predicts actions based on Transformer and Graph Convolutional Network (GCN). In contrast, GPN is based on GCN and Q-network that receives the LPN states, traffic flow and road information to manage intersections to provide a signal-free corridor. We developed the Deep Graph Convolution Q-Network (DGCQ) by combining Deep Q-Network (DQN) and GCN to achieve a signal-free corridor. DGCQ leverages GCN's intersection collaboration and DQN's information aggregation for traffic control decisions Proposed CCGN model is trained on the robust synthetic traffic network and evaluated on the real-world traffic networks that outperform the other state-of-the-art models." @default.
- W4385358041 created "2023-07-29" @default.
- W4385358041 creator A5002957863 @default.
- W4385358041 creator A5031758867 @default.
- W4385358041 creator A5071482846 @default.
- W4385358041 creator A5081865875 @default.
- W4385358041 date "2023-09-01" @default.
- W4385358041 modified "2023-09-26" @default.
- W4385358041 title "CCGN: Centralized collaborative graphical transformer multi-agent reinforcement learning for multi-intersection signal free-corridor" @default.
- W4385358041 cites W1889582480 @default.
- W4385358041 cites W1969758122 @default.
- W4385358041 cites W2043256010 @default.
- W4385358041 cites W2465720902 @default.
- W4385358041 cites W2734335288 @default.
- W4385358041 cites W2862204210 @default.
- W4385358041 cites W2907400790 @default.
- W4385358041 cites W2914650334 @default.
- W4385358041 cites W2915117209 @default.
- W4385358041 cites W2963027910 @default.
- W4385358041 cites W2964255692 @default.
- W4385358041 cites W2965163470 @default.
- W4385358041 cites W2996369207 @default.
- W4385358041 cites W2998590388 @default.
- W4385358041 cites W3011507876 @default.
- W4385358041 cites W3014845548 @default.
- W4385358041 cites W3029232882 @default.
- W4385358041 cites W3047275536 @default.
- W4385358041 cites W3102059892 @default.
- W4385358041 cites W3115989973 @default.
- W4385358041 cites W3131379668 @default.
- W4385358041 cites W3133129631 @default.
- W4385358041 cites W3139071578 @default.
- W4385358041 cites W3167586364 @default.
- W4385358041 cites W3211080667 @default.
- W4385358041 cites W3211108575 @default.
- W4385358041 cites W4210742101 @default.
- W4385358041 cites W4221155364 @default.
- W4385358041 cites W4281686250 @default.
- W4385358041 cites W4284879547 @default.
- W4385358041 cites W4289779215 @default.
- W4385358041 cites W4311987441 @default.
- W4385358041 cites W4313431515 @default.
- W4385358041 cites W4318162656 @default.
- W4385358041 cites W4319335480 @default.
- W4385358041 cites W4327704813 @default.
- W4385358041 doi "https://doi.org/10.1016/j.neunet.2023.07.027" @default.
- W4385358041 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37549608" @default.
- W4385358041 hasPublicationYear "2023" @default.
- W4385358041 type Work @default.
- W4385358041 citedByCount "0" @default.
- W4385358041 crossrefType "journal-article" @default.
- W4385358041 hasAuthorship W4385358041A5002957863 @default.
- W4385358041 hasAuthorship W4385358041A5031758867 @default.
- W4385358041 hasAuthorship W4385358041A5071482846 @default.
- W4385358041 hasAuthorship W4385358041A5081865875 @default.
- W4385358041 hasBestOaLocation W43853580411 @default.
- W4385358041 hasConcept C119599485 @default.
- W4385358041 hasConcept C120314980 @default.
- W4385358041 hasConcept C127413603 @default.
- W4385358041 hasConcept C132525143 @default.
- W4385358041 hasConcept C154945302 @default.
- W4385358041 hasConcept C165801399 @default.
- W4385358041 hasConcept C22212356 @default.
- W4385358041 hasConcept C31258907 @default.
- W4385358041 hasConcept C41008148 @default.
- W4385358041 hasConcept C64543145 @default.
- W4385358041 hasConcept C66322947 @default.
- W4385358041 hasConcept C79403827 @default.
- W4385358041 hasConcept C80444323 @default.
- W4385358041 hasConcept C97541855 @default.
- W4385358041 hasConceptScore W4385358041C119599485 @default.
- W4385358041 hasConceptScore W4385358041C120314980 @default.
- W4385358041 hasConceptScore W4385358041C127413603 @default.
- W4385358041 hasConceptScore W4385358041C132525143 @default.
- W4385358041 hasConceptScore W4385358041C154945302 @default.
- W4385358041 hasConceptScore W4385358041C165801399 @default.
- W4385358041 hasConceptScore W4385358041C22212356 @default.
- W4385358041 hasConceptScore W4385358041C31258907 @default.
- W4385358041 hasConceptScore W4385358041C41008148 @default.
- W4385358041 hasConceptScore W4385358041C64543145 @default.
- W4385358041 hasConceptScore W4385358041C66322947 @default.
- W4385358041 hasConceptScore W4385358041C79403827 @default.
- W4385358041 hasConceptScore W4385358041C80444323 @default.
- W4385358041 hasConceptScore W4385358041C97541855 @default.
- W4385358041 hasLocation W43853580411 @default.
- W4385358041 hasLocation W43853580412 @default.
- W4385358041 hasOpenAccess W4385358041 @default.
- W4385358041 hasPrimaryLocation W43853580411 @default.
- W4385358041 hasRelatedWork W260766989 @default.
- W4385358041 hasRelatedWork W2959276766 @default.
- W4385358041 hasRelatedWork W3005880661 @default.
- W4385358041 hasRelatedWork W3044695623 @default.
- W4385358041 hasRelatedWork W3049333768 @default.
- W4385358041 hasRelatedWork W3074294383 @default.
- W4385358041 hasRelatedWork W3139193008 @default.
- W4385358041 hasRelatedWork W3212758104 @default.
- W4385358041 hasRelatedWork W4206669594 @default.
- W4385358041 hasRelatedWork W4295941380 @default.