How to Learn from Risk: Explicit Risk-Utility Reinforcement Learning for Efficient and Safe Driving Strategies

Schmidt LM, Rietsch S, Plinge A, Eskofier B, Mutschler C (2022)

Publication Type: Conference contribution

Publication year: 2022

Publisher: Institute of Electrical and Electronics Engineers Inc.

Book Volume: 2022-October

Pages Range: 1913-1920

Conference Proceedings Title: IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

Event location: Macau, CHN

ISBN: 9781665468800

DOI: 10.1109/ITSC55140.2022.9922345

Abstract

Autonomous driving has the potential to revolutionize mobility and is hence an active area of research. In practice, the behavior of autonomous vehicles must be acceptable, i.e., efficient, safe, and interpretable. While vanilla reinforcement learning (RL) finds performant behavioral strategies, they are often unsafe and uninterpretable. Safety is introduced through Safe RL approaches, but they still mostly remain un-interpretable as the learned behavior is jointly optimized for safety and performance without modeling them separately. Interpretable machine learning is rarely applied to RL. This work proposes SafeDQN, which allows making the behavior of autonomous vehicles safe and interpretable while still being efficient. SafeDQN offers an understandable, semantic trade-off between the expected risk and the utility of actions while being algorithmically transparent. We show that SafeDQN finds interpretable and safe driving policies for various scenarios and demonstrate how state-of-the-art saliency techniques can help assess risk and utility.

Authors with CRIS profile

Björn Eskofier Machine Learning and Data Analytics Lab

Involved external institutions

Fraunhofer-Institut für Integrierte Schaltungen (IIS) DE Germany (DE)

How to cite

APA:

Schmidt, L.M., Rietsch, S., Plinge, A., Eskofier, B., & Mutschler, C. (2022). How to Learn from Risk: Explicit Risk-Utility Reinforcement Learning for Efficient and Safe Driving Strategies. In IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC (pp. 1913-1920). Macau, CHN: Institute of Electrical and Electronics Engineers Inc..

MLA:

Schmidt, Lukas M., et al. "How to Learn from Risk: Explicit Risk-Utility Reinforcement Learning for Efficient and Safe Driving Strategies." Proceedings of the 25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022, Macau, CHN Institute of Electrical and Electronics Engineers Inc., 2022. 1913-1920.

BibTeX: Download