Towards Safe Reinforcement Learning via OOD Dynamics Detection in Autonomous Driving System (Student Abstract)
Keywords:Out-of-Distribution, AI Safety, Safe Reinforcement Learning, Deep Reinforcement Learning Autonomous Driving
AbstractDeep reinforcement learning (DRL) has proven effective in training agents to achieve goals in complex environments. However, a trained RL agent may exhibit, during deployment, unexpected behavior when faced with a situation where its state transitions differ even slightly from the training environment. Such a situation can arise for a variety of reasons. Rapid and accurate detection of anomalous behavior appears to be a prerequisite for using DRL in safety-critical systems, such as autonomous driving. We propose a novel OOD detection algorithm based on modeling the transition function of the training environment. Our method captures the bias of model behavior when encountering subtle changes of dynamics while maintaining a low false positive rate. Preliminary evaluations on the realistic simulator CARLA corroborate the relevance of our proposed method.
How to Cite
Gardille, A., & Ahmad, O. (2023). Towards Safe Reinforcement Learning via OOD Dynamics Detection in Autonomous Driving System (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16216-16217. https://doi.org/10.1609/aaai.v37i13.26968
AAAI Student Abstract and Poster Program