Transfer Learning for Efficient Iterative Safety Validation

TL;DR

This paper introduces a transfer learning approach to enhance the efficiency of reinforcement learning-based safety validation for autonomous systems, reducing computational effort and improving performance across related tasks.

Contribution

The paper proposes a novel transfer learning method that encodes and transfers knowledge via action value functions and attention weights, improving safety validation efficiency for related systems.

Findings

Transfer learning improves initial validation performance.

Reduces training steps needed for safety validation.

Effective across gridworld and autonomous driving scenarios.

Abstract

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.