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

Thumbnail Image
Files
019-023.pdf (1.37 MB)
1022-file1.mp4 (30.85 MB)
Date
2022
Authors
Metz, Yannick
Schlegel, Udo
Seebacher, Daniel
El-Assady, Mennatallah
Keim, Daniel
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Multiple 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.
Description

CCS Concepts: Human-centered computing --> Visual analytics; Computing methodologies --> Reinforcement learning

        
@inproceedings{
10.2312:eurova.20221074
,
booktitle = {
EuroVis Workshop on Visual Analytics (EuroVA)
},
editor = {
Bernard, Jürgen
 and 
Angelini, Marco
},
title = {{
A Comprehensive Workflow for Effective Imitation and Reinforcement Learning with Visual Analytics
}},
author = {
Metz, Yannick
 and 
Schlegel, Udo
 and 
Seebacher, Daniel
 and 
El-Assady, Mennatallah
 and 
Keim, Daniel
},
year = {
2022
},
publisher = {
The Eurographics Association
},
ISSN = {
2664-4487
},
ISBN = {
978-3-03868-183-0
},
DOI = {
10.2312/eurova.20221074
}
}
Citation
URI
https://doi.org/10.2312/eurova.20221074
 https://diglib.eg.org:443/handle/10.2312/eurova20221074
Collections
EuroVA2022