Shield Synthesis for Safe Reinforcement Learning RoderickBloem TUGraz Austria Shield Synthesis for Safe Reinforcement Learning 824B255E76B04746AC09F4C54F3EEC0B GROBID - A machine learning software for extracting information from scholarly documents

You have a reinforcement learning system? Sure, it works great, but does it give you any guarantees? I thought not.

We will describe methods to use reactive synthesis to construct runtime enforcement modules (shields) that can ensure that a system works correctly, even if the system has bugs. If the system doesn't have too many bugs, the behavior of the shielded system will stay close to the behavior of the original system. We will show extensions in probabilistic and timed settings.