Finding Safe Zones of Markov Decision Processes Policies Lee Cohen Yishay Mansour Michal Moshkovitz TTI-Chicago Tel-Aviv University Bosch Center for AI Google Research

One notable exception to that is Safe RL which addresses the concept of safety. Traditional Safe RL focuses on finding the best policy that meets safety requirements, typically by either adjusting the objective to include the safety requirements and then optimizing for it, or incorporating additional safety constraints to the exploration. In both of these cases, the safety requirements should be pre-specified. Anomaly Detection is the problem of identifying patterns in data that are unexpected, i.e., anomalies (see, e.g., Chandola et al. (2009) for survey).