Transfer Learning for Efficient Iterative Safety Validation
This work aims to reduce the computational burden of safety validation for developers of safety-critical autonomous systems, representing an incremental improvement in efficiency.
This paper addresses the computational cost of safety validation for autonomous systems by applying transfer learning to reinforcement learning-based validation algorithms. By transferring knowledge from previous tasks, the method improves initial and final performance and reduces the number of training steps in gridworld and autonomous driving scenarios.
Safety validation is important during the development of safety-critical autonomous systems but can require significant computational effort. Existing algorithms often start from scratch each time the system under test changes. We apply transfer learning to improve the efficiency of reinforcement learning based safety validation algorithms when applied to related systems. Knowledge from previous safety validation tasks is encoded through the action value function and transferred to future tasks with a learned set of attention weights. Including a learned state and action value transformation for each source task can improve performance even when systems have substantially different failure modes. We conduct experiments on safety validation tasks in gridworld and autonomous driving scenarios. We show that transfer learning can improve the initial and final performance of validation algorithms and reduce the number of training steps.