Under CopyrightHaider, TomTomHaiderSchmoeller Roza, FelippeFelippeSchmoeller RozaEilers, DirkDirkEilersRoscher, KarstenKarstenRoscherGünnemann, StephanStephanGünnemann2022-03-1521.9.20212021https://publica.fraunhofer.de/handle/publica/41209310.24406/publica-fhg-412093End-to-End Deep Reinforcement Learning (RL) systems return an action no matter what situation they are confronted with, even for situations that differ entirely from those an agent has been trained for. In this work, we propose to formalize the changes in the environment in terms of the Markov Decision Process (MDP), resulting in a more formal framework when dealing with such problems.enreinforcement learningRLsafety criticalMarkov Decision ProcessMDPsafetySafe Intelligencerobustnessdomain shiftout of distributionposter