Workshop: XXAI: Extending Explainable AI Beyond Deep Models and Classifiers
Invited Talk 8: Osbert Bastani - Interpretable, Robust, and Verifiable Reinforcement Learning
Structured control policies such as decision trees, finite-state machines, and programs have a number of advantages over more traditional models: they are easier for humans to understand and debug, they generalize more robustly to novel environments, and they are easier to formally verify. However, learning these kinds of models has proven to be challenging. I will describe recent progress learning structured policies, along with evidence demonstrating their benefits.