Visualizing the Evolution of Multi-agent Game-playing Behaviors

Simple item page
dc.contributor.authorAgarwal, Shivamen_US
dc.contributor.authorLatif, Shahiden_US
dc.contributor.authorRothweiler, Aristideen_US
dc.contributor.authorBeck, Fabianen_US
dc.contributor.editorKrone, Michaelen_US
dc.contributor.editorLenti, Simoneen_US
dc.contributor.editorSchmidt, Johannaen_US
dc.date.accessioned2022-06-02T15:29:03Z
dc.date.available2022-06-02T15:29:03Z
dc.date.issued2022
dc.description.abstractAnalyzing the training evolution of AI agents in a multi-agent environment helps to understand changes in learned behaviors, as well as the sequence in which they are learned. We train an existing Pommerman team from scratch and, at regular intervals, let it battle against another top-performing team. We define thirteen game-specific behaviors and compute their occurrences in 600 matches. To investigate the evolution of these behaviors, we propose a visualization approach and showcase its usefulness in an application example.en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationEuroVis 2022 - Posters
dc.identifier.doi10.2312/evp.20221111
dc.identifier.isbn978-3-03868-185-4
dc.identifier.pages23-25
dc.identifier.pages3 pages
dc.identifier.urihttps://doi.org/10.2312/evp.20221111
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/evp20221111
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectMulti-agent system, multivariate data, evolving gameplay behaviors, AI training, visualization
dc.subjectMulti
dc.subjectagent system
dc.subjectmultivariate data
dc.subjectevolving gameplay behaviors
dc.subjectAI training
dc.subjectvisualization
dc.titleVisualizing the Evolution of Multi-agent Game-playing Behaviorsen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
023-025.pdf
Size:
671.79 KB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
7673-file1.zip
Size:
16.2 MB
Format:
Zip file
Download
Collections
EuroVisPosters2022