Reinforcement Learning with Probabilistic Guarantees for Autonomous Driving [article]

Maxime Bouton, Jesper Karlsson, Alireza Nakhaei, Kikuo Fujimura, Mykel J. Kochenderfer, Jana Tumova
2019 arXiv   pre-print
Designing reliable decision strategies for autonomous urban driving is challenging. Reinforcement learning (RL) has been used to automatically derive suitable behavior in uncertain environments, but it does not provide any guarantee on the performance of the resulting policy. We propose a generic approach to enforce probabilistic guarantees on an RL agent. An exploration strategy is derived prior to training that constrains the agent to choose among actions that satisfy a desired probabilistic
more » ... pecification expressed with linear temporal logic (LTL). Reducing the search space to policies satisfying the LTL formula helps training and simplifies reward design. This paper outlines a case study of an intersection scenario involving multiple traffic participants. The resulting policy outperforms a rule-based heuristic approach in terms of efficiency while exhibiting strong guarantees on safety.
arXiv:1904.07189v2 fatcat:fxsjjitdeven3a56jn6oxxohbm