![Aurora over trees](https://safe-intelligence.fraunhofer.de/transforms/images/articles/2022-04-28-out-of-distribution-detection-fuer-reinforcement-learning/_360x540_crop_center-center_90_none/iStock-640201826-Widewingsstudio.jpg)
Machine learning
Out-of-distribution detection for reinforcement learning
How can intelligent systems learn to perform tasks – and do so simply by interacting with their environment? This is the subject of reinforcement learning, a subfield of machine learning. Problems occur primarily when situations arise that the system is not yet familiar with.