Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289779215> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4289779215 endingPage "262" @default.
- W4289779215 startingPage "249" @default.
- W4289779215 abstract "Adaptive traffic signal control (ATSC) facilitates alleviating traffic congestion. Multi-agent deep reinforcement learning (MDRL) is a new promising algorithm for ATSC, and Graph Neural Networks (GNNs) further promote its learning ability. However, there are some drawbacks in the state-of-the-art MDRL algorithms. (1) These algorithms cannot effectively fuse diverse heterogeneous information of traffic networks due to adopting homogeneous GNNs; (2) These algorithms cannot be effectively trained due to merely adopting MDRL loss functions. In this paper, we propose an Inductive Heterogeneous graph Attention-based Multi-agent Deep Graph Infomax (IHA-MDGI) algorithm for ATSC. The proposed IHA-MDGI algorithm conducts both feature fusion via a proposed Inductive Heterogeneous graph Attention (IHA) algorithm and training via a proposed Multi-agent Deep Graph Infomax (MDGI) framework. Specifically, (1) Unlike the algorithms which adopt homogeneous GNNs, in the IHA algorithm, heterogeneous GNNs are designed to fuse both heterogeneous structural information and heterogeneous features of traffic networks, which aims to acquire heterogeneous information embeddings of traffic networks. (2) In the MDGI framework, the acquired embeddings are used to calculate the signal-control policies and Q-value for each agent, and then a mutual-information loss function is designed, which combines with the MDRL loss function to jointly train the whole algorithm. The designed mutual-information loss function focuses on maximizing mutual information between input (i.e., heterogeneous information embeddings) and output (i.e., Q-value), which can produce cooperative signal-control policies and maximize Q-value. We conduct the experiments in both real-traffic and synthetic-traffic networks under the time-varying traffic flows, and the results demonstrate that IHA-MDGI algorithm outperforms the state-of-the-art MDRL algorithms about multiple metrics." @default.
- W4289779215 created "2022-08-04" @default.
- W4289779215 creator A5014822993 @default.
- W4289779215 creator A5038425463 @default.
- W4289779215 date "2022-12-01" @default.
- W4289779215 modified "2023-09-30" @default.
- W4289779215 title "An inductive heterogeneous graph attention-based multi-agent deep graph infomax algorithm for adaptive traffic signal control" @default.
- W4289779215 cites W1564229684 @default.
- W4289779215 cites W2064675550 @default.
- W4289779215 cites W2088595989 @default.
- W4289779215 cites W2125001944 @default.
- W4289779215 cites W2145339207 @default.
- W4289779215 cites W2146087064 @default.
- W4289779215 cites W2153002112 @default.
- W4289779215 cites W2618530766 @default.
- W4289779215 cites W2623391631 @default.
- W4289779215 cites W2767547957 @default.
- W4289779215 cites W2947033529 @default.
- W4289779215 cites W2952613166 @default.
- W4289779215 cites W2953683172 @default.
- W4289779215 cites W2964255692 @default.
- W4289779215 cites W3000301417 @default.
- W4289779215 cites W3101245099 @default.
- W4289779215 cites W3139071578 @default.
- W4289779215 cites W5525483 @default.
- W4289779215 doi "https://doi.org/10.1016/j.inffus.2022.08.001" @default.
- W4289779215 hasPublicationYear "2022" @default.
- W4289779215 type Work @default.
- W4289779215 citedByCount "7" @default.
- W4289779215 countsByYear W42897792152023 @default.
- W4289779215 crossrefType "journal-article" @default.
- W4289779215 hasAuthorship W4289779215A5014822993 @default.
- W4289779215 hasAuthorship W4289779215A5038425463 @default.
- W4289779215 hasConcept C108037233 @default.
- W4289779215 hasConcept C119599485 @default.
- W4289779215 hasConcept C120317606 @default.
- W4289779215 hasConcept C127162648 @default.
- W4289779215 hasConcept C127413603 @default.
- W4289779215 hasConcept C132525143 @default.
- W4289779215 hasConcept C141353440 @default.
- W4289779215 hasConcept C152139883 @default.
- W4289779215 hasConcept C153402090 @default.
- W4289779215 hasConcept C154945302 @default.
- W4289779215 hasConcept C158207573 @default.
- W4289779215 hasConcept C31258907 @default.
- W4289779215 hasConcept C41008148 @default.
- W4289779215 hasConcept C555944384 @default.
- W4289779215 hasConcept C76155785 @default.
- W4289779215 hasConcept C80444323 @default.
- W4289779215 hasConceptScore W4289779215C108037233 @default.
- W4289779215 hasConceptScore W4289779215C119599485 @default.
- W4289779215 hasConceptScore W4289779215C120317606 @default.
- W4289779215 hasConceptScore W4289779215C127162648 @default.
- W4289779215 hasConceptScore W4289779215C127413603 @default.
- W4289779215 hasConceptScore W4289779215C132525143 @default.
- W4289779215 hasConceptScore W4289779215C141353440 @default.
- W4289779215 hasConceptScore W4289779215C152139883 @default.
- W4289779215 hasConceptScore W4289779215C153402090 @default.
- W4289779215 hasConceptScore W4289779215C154945302 @default.
- W4289779215 hasConceptScore W4289779215C158207573 @default.
- W4289779215 hasConceptScore W4289779215C31258907 @default.
- W4289779215 hasConceptScore W4289779215C41008148 @default.
- W4289779215 hasConceptScore W4289779215C555944384 @default.
- W4289779215 hasConceptScore W4289779215C76155785 @default.
- W4289779215 hasConceptScore W4289779215C80444323 @default.
- W4289779215 hasFunder F4320321001 @default.
- W4289779215 hasLocation W42897792151 @default.
- W4289779215 hasOpenAccess W4289779215 @default.
- W4289779215 hasPrimaryLocation W42897792151 @default.
- W4289779215 hasRelatedWork W1833833977 @default.
- W4289779215 hasRelatedWork W2121768227 @default.
- W4289779215 hasRelatedWork W2139138217 @default.
- W4289779215 hasRelatedWork W2142105644 @default.
- W4289779215 hasRelatedWork W2146711600 @default.
- W4289779215 hasRelatedWork W2937967841 @default.
- W4289779215 hasRelatedWork W3190432377 @default.
- W4289779215 hasRelatedWork W4225284605 @default.
- W4289779215 hasRelatedWork W4225388699 @default.
- W4289779215 hasRelatedWork W4295992366 @default.
- W4289779215 hasVolume "88" @default.
- W4289779215 isParatext "false" @default.
- W4289779215 isRetracted "false" @default.
- W4289779215 workType "article" @default.