MDPFuzz: testing models solving Markov decision processes
Qi Pang, Yuanyuan Yuan, Shuai Wang
Abstract
The Markov decision process (MDP) provides a mathematical frame- work for modeling sequential decision-making problems, many of which are crucial to security and safety, such as autonomous driving and robot control. The rapid development of artificial intelligence research has created efficient methods for solving MDPs, such as deep neural networks (DNNs), reinforcement learning (RL), and imitation learning (IL). However, these popular models solving MDPs are neither thoroughly tested nor rigorously reliable.
Topics & Concepts
Markov decision processComputer scienceReinforcement learningArtificial intelligenceMachine learningFrame (networking)Partially observable Markov decision processMarkov processProcess (computing)ImitationRobotMarkov chainMarkov modelMathematicsTelecommunicationsPsychologyStatisticsSocial psychologyOperating systemAdversarial Robustness in Machine LearningAutonomous Vehicle Technology and SafetyAnomaly Detection Techniques and Applications