Learning to identify safety-critical scenarios for an autonomous vehicle

A methods and system for learning to identify safety-critical scenarios for autonomous vehicles. First state information representing a first state of a driving scenario is received 702. The information includes a state of a vehicle and a state of an agent in the vehicle's environment. The first state information is processed with a neural network to determine at least one action to be performed by the agent, including a perception degradation action causing misperception of the agent by a perception system of the vehicle 704. Second state information representing a second state of the driving scenario is received after performance of the at least one action 706. A reward for the action is determined 708. First and second distances between the vehicle and the agent are determined 710 & 712 and compared to determine the reward for the at least one action wherein the reward is greater when the second distance meets the first 714. At least one weight of the neural network is adjusted based on the reward 716.