Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287255935> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4287255935 abstract "Recent work in the multi-agent domain has shown the promise of Graph Neural Networks (GNNs) to learn complex coordination strategies. However, most current approaches use minor variants of a Graph Convolutional Network (GCN), which applies a convolution to the communication graph formed by the multi-agent system. In this paper, we investigate whether the performance and generalization of GCNs can be improved upon. We introduce ModGNN, a decentralized framework which serves as a generalization of GCNs, providing more flexibility. To test our hypothesis, we evaluate an implementation of ModGNN against several baselines in the multi-agent flocking problem. We perform an ablation analysis to show that the most important component of our framework is one that does not exist in a GCN. By varying the number of agents, we also demonstrate that an application-agnostic implementation of ModGNN possesses an improved ability to generalize to new environments." @default.
- W4287255935 created "2022-07-25" @default.
- W4287255935 creator A5066624177 @default.
- W4287255935 creator A5068296171 @default.
- W4287255935 date "2021-03-24" @default.
- W4287255935 modified "2023-09-30" @default.
- W4287255935 title "ModGNN: Expert Policy Approximation in Multi-Agent Systems with a Modular Graph Neural Network Architecture" @default.
- W4287255935 doi "https://doi.org/10.48550/arxiv.2103.13446" @default.
- W4287255935 hasPublicationYear "2021" @default.
- W4287255935 type Work @default.
- W4287255935 citedByCount "0" @default.
- W4287255935 crossrefType "posted-content" @default.
- W4287255935 hasAuthorship W4287255935A5066624177 @default.
- W4287255935 hasAuthorship W4287255935A5068296171 @default.
- W4287255935 hasBestOaLocation W42872559351 @default.
- W4287255935 hasConcept C101468663 @default.
- W4287255935 hasConcept C111919701 @default.
- W4287255935 hasConcept C119857082 @default.
- W4287255935 hasConcept C120314980 @default.
- W4287255935 hasConcept C132525143 @default.
- W4287255935 hasConcept C134306372 @default.
- W4287255935 hasConcept C154945302 @default.
- W4287255935 hasConcept C177148314 @default.
- W4287255935 hasConcept C33923547 @default.
- W4287255935 hasConcept C41008148 @default.
- W4287255935 hasConcept C80444323 @default.
- W4287255935 hasConceptScore W4287255935C101468663 @default.
- W4287255935 hasConceptScore W4287255935C111919701 @default.
- W4287255935 hasConceptScore W4287255935C119857082 @default.
- W4287255935 hasConceptScore W4287255935C120314980 @default.
- W4287255935 hasConceptScore W4287255935C132525143 @default.
- W4287255935 hasConceptScore W4287255935C134306372 @default.
- W4287255935 hasConceptScore W4287255935C154945302 @default.
- W4287255935 hasConceptScore W4287255935C177148314 @default.
- W4287255935 hasConceptScore W4287255935C33923547 @default.
- W4287255935 hasConceptScore W4287255935C41008148 @default.
- W4287255935 hasConceptScore W4287255935C80444323 @default.
- W4287255935 hasLocation W42872559351 @default.
- W4287255935 hasOpenAccess W4287255935 @default.
- W4287255935 hasPrimaryLocation W42872559351 @default.
- W4287255935 hasRelatedWork W1515507694 @default.
- W4287255935 hasRelatedWork W2054640521 @default.
- W4287255935 hasRelatedWork W2126957398 @default.
- W4287255935 hasRelatedWork W2801603084 @default.
- W4287255935 hasRelatedWork W2905476450 @default.
- W4287255935 hasRelatedWork W2961085424 @default.
- W4287255935 hasRelatedWork W2989932438 @default.
- W4287255935 hasRelatedWork W2998813341 @default.
- W4287255935 hasRelatedWork W32863620 @default.
- W4287255935 hasRelatedWork W4224009465 @default.
- W4287255935 isParatext "false" @default.
- W4287255935 isRetracted "false" @default.
- W4287255935 workType "article" @default.