Glyph-Based Visual Analysis of Q-Learning Based Action Policy Ensembles on Racetrack
Abstract
Recently, deep reinforcement learning has become very successful in making complex decisions, achieving super-human performance in Go, chess, and challenging video games. When applied to safety-critical applications, however, like the control of cyber-physical systems with a learned action policy, the need for certification arises. To empower domain experts to decide whether to trust a learned action policy, we propose visualization methods for a detailed assessment of action policies implemented as neural networks trained with Q-learning. We propose a highly responsive visual analysis tool that fosters efficient analysis of Q-learning based action policies over the complete state space of the system, which is essential for verification and gaining detailed insights on policy quality. For efficient visual inspection of the per-action Q-value rating over the state space, we designed three glyphs that provide different …
Cite
@inproceedings{grossGlyphBasedVisualAnalysisOf2022,
author = {David Groß and Michaela Klauck and Timo P. Gros and Marcel Steinmetz and Joerg Hoffmann and Stefan Gumhold},
booktitle = {International Conference on Information Visualisation (IV'22). International Conference on Information Visualisation (IV-2022), 26th International Conference on Information Visualisation, July 19-22, Vienna, Austria},
doi = {10.1109/IV56949.2022.00011},
isbn = {978-1-6654-9008-5},
publisher = {IEEE},
title = {Glyph-Based Visual Analysis of Q-Learning Based Action Policy Ensembles on Racetrack},
year = {2022}
}