Detection of Important States through an Iterative Q-value Algorithm for Explainable Reinforcement Learning

Simple item page
dc.contributor.authorMilani, Rudy
dc.contributor.authorMoll, Maximilian
dc.contributor.authorDe Leone, Renato
dc.date.accessioned2023-12-26T18:37:06Z
dc.date.available2023-12-26T18:37:06Z
dc.date.issued2024-01-03
dc.identifier.doi10.24251/HICSS.2024.174
dc.identifier.isbn978-0-9981331-7-1
dc.identifier.other13df9219-88ea-4b3a-bbc8-69115062495c
dc.identifier.urihttps://hdl.handle.net/10125/106551
dc.language.isoeng
dc.relation.ispartofProceedings of the 57th Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectIntelligent Decision Support on Networks – Data-driven Optimization, Augmented and Explainable AI in Complex Supply Chains
dc.subjectexplainable reinforcement learning
dc.subjectimportance analysis
dc.subjectimportant states
dc.subjectsafe reinforcement learning
dc.titleDetection of Important States through an Iterative Q-value Algorithm for Explainable Reinforcement Learning
dc.typeConference Paper
dc.type.dcmiText
dcterms.abstractTo generate safe and trustworthy Reinforcement Learning agents, it is fundamental to recognize meaningful states where a particular action should be performed. Thus, it is possible to produce more accurate explanations of the behaviour of the trained agent and simultaneously reduce the risk of committing a fatal error. In this study, we improve existing metrics using Q-values to detect essential states in Reinforcement Learning by introducing a scaled iterated algorithm called IQVA. The key observation of our approach is that a state is important not only if the action has a high impact but also if it often appears in different episodes. We compared our approach with the two baseline measures and a newly introduced value in grid-world environments to demonstrate its efficacy. In this way, we show how the proposed methodology can highlight only the meaningful states for that particular agent instead of emphasizing the importance of states that are rarely visited.
dcterms.extent8 pages
prism.startingpage1401

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0136.pdf
Size:
873.77 KB
Format:
Adobe Portable Document Format
Download

Collections

Intelligent Decision Support on Networks - Data-driven Optimization, Augmented and Explainable AI in Complex Supply Chains