A Comprehensive Workflow for Effective Imitation and Reinforcement Learning with Visual Analytics

Simple item page
dc.contributor.authorMetz, Yannicken_US
dc.contributor.authorSchlegel, Udoen_US
dc.contributor.authorSeebacher, Danielen_US
dc.contributor.authorEl-Assady, Mennatallahen_US
dc.contributor.authorKeim, Danielen_US
dc.contributor.editorBernard, Jürgenen_US
dc.contributor.editorAngelini, Marcoen_US
dc.date.accessioned2022-06-02T14:59:49Z
dc.date.available2022-06-02T14:59:49Z
dc.date.issued2022
dc.description.abstractMultiple challenges hinder the application of reinforcement learning algorithms in experimental and real-world use cases even with recent successes in such areas. Such challenges occur at different stages of the development and deployment of such models. While reinforcement learning workflows share similarities with machine learning approaches, we argue that distinct challenges can be tackled and overcome using visual analytic concepts. Thus, we propose a comprehensive workflow for reinforcement learning and present an implementation of our workflow incorporating visual analytic concepts integrating tailored views and visualizations for different stages and tasks of the workflow.en_US
dc.description.sectionheadersHuman-Model Collaboration and Personalization
dc.description.seriesinformationEuroVis Workshop on Visual Analytics (EuroVA)
dc.identifier.doi10.2312/eurova.20221074
dc.identifier.isbn978-3-03868-183-0
dc.identifier.issn2664-4487
dc.identifier.pages19-23
dc.identifier.pages5 pages
dc.identifier.urihttps://doi.org/10.2312/eurova.20221074
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/eurova20221074
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Human-centered computing --> Visual analytics; Computing methodologies --> Reinforcement learning
dc.subjectHuman centered computing
dc.subjectVisual analytics
dc.subjectComputing methodologies
dc.subjectReinforcement learning
dc.titleA Comprehensive Workflow for Effective Imitation and Reinforcement Learning with Visual Analyticsen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
019-023.pdf
Size:
1.37 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
1022-file1.mp4
Size:
30.85 MB
Format:
Unknown data format
Download
Collections
EuroVA2022