The Adaptive Stress Testing Formulation

Mark Koren, Anthony Corso, Mykel Kochenderfer

Keywords: Validation, Safe Autonomy, Simulation, Reinforcement Learning, Markov Decision Processes

TL;DR: A formulation for a black-box, reinforcement learning method to find the most-likely failure of a system acting in complex scenarios.

Abstract: Validation is a key challenge in the search for safe autonomy. Simulations are often either too simple to provide robust validation, or too complex to tractably compute. Therefore, approximate validation methods are needed to tractably find failures without unsafe simplifications. This paper presents the theory behind one such black-box approach: adaptive stress testing (AST). We also provide three examples of validation problems formulated to work with AST.