Transfer Learning for Efficient Iterative Safety Validation

Authors

  • Anthony Corso Stanford University
  • Mykel J. Kochenderfer Stanford University

Keywords:

Adversarial Learning & Robustness, Reinforcement Learning

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.

Downloads

Published

2021-05-18

How to Cite

Corso, A., & Kochenderfer, M. J. (2021). Transfer Learning for Efficient Iterative Safety Validation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(8), 7125-7132. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16876

Issue

Section

AAAI Technical Track on Machine Learning I