Reinforcement Learning with Probabilistic Guarantees for Autonomous Driving

Abstract

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 specification 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.

References in corpus (1)

• Congested Traffic States in Empirical Observations and Microscopic Simulations

Cited by in corpus (10)

• A Survey of Deep RL and IL for Autonomous Driving Policy Learning
• A Survey on Autonomous Vehicle Control in the Era of Mixed-Autonomy: From Physics-Based to AI-Guided Driving Policy Learning
• Safe Reinforcement Learning via Probabilistic Shields
• Learning Interaction-aware Guidance Policies for Motion Planning in Dense Traffic Scenarios
• Learning Optimal Strategies for Temporal Tasks in Stochastic Games
• A Survey of Deep Reinforcement Learning Algorithms for Motion Planning and Control of Autonomous Vehicles
• Quantifying Assurance in Learning-enabled Systems
• Provably Efficient Model-Free Algorithm for MDPs with Peak Constraints
• Reconnaissance and Planning algorithm for constrained MDP
• Neural Network Repair with Reachability Analysis