Lab Conditions for Research on Explainable Automated Decisions

Abstract

Artificial neural networks are being proposed for automated decision making under uncertainty in many visionary contexts, including high-stake tasks such as navigating autonomous cars through dense traffic. Against this background, it is imperative that the decision making entities meet central societal desiderata regarding dependability, perspicuity, explainability, and robustness. Decision making problems under uncertainty are typically captured formally as variations of Markov decision processes (MDPs). This paper discusses a set of natural and easy-to-control abstractions, based on the Racetrack benchmarks and extensions thereof, that altogether connect the autonomous driving challenge to the modelling world of MDPs. This is then used to study the dependability and robustness of NN-based decision entities, which in turn are based on state-of-the-art NN learning techniques.

@inproceedings{baierLabConditionsForResearch2021,
 author = {Christel Baier and Maria Christakis and Timo P. Gros and David Groß and Stefan Gumhold and Holger Hermanns and Jörg Hoffmann and Michaela Klauck},
 booktitle = {Trustworthy AI--Integrating Learning, Optimization and Reasoning: First International Workshop, TAILOR 2020, Virtual Event, September 4--5, 2020, Revised Selected Papers. Workshop on Foundations of Trustworthy AI integrating Learning, Optimisation and Reasoning (TAILOR-2020), located at First International Workshop, April 4-5, Virtual Event},
 organization = {Springer Nature},
 publisher = {Springer Nature},
 title = {Lab Conditions for Research on Explainable Automated Decisions},
 year = {2021}
}