: The paper introduces CaRL , a reinforcement learning (RL) planner for autonomous driving. It achieves state-of-the-art results on benchmarks like longest6 v2 and nuPlan , significantly outperforming prior methods such as "Roach" by reducing collisions and improving planning efficiency. Software and Resources
: Bernhard Jaeger, Daniel Dauner, Jens Beißwenger, Simon Gerstenecker, Kashyap Chitta, and Andreas Geiger File: C.A.R.L.v1.0.zip ...
: CaRL: Learning Scalable Planning Policies with Simple Rewards : The paper introduces CaRL , a reinforcement
: The first public codebase for doing Reinforcement Learning with the CARLA autonomous driving simulator leaderboard. : The paper introduces CaRL
: A 2026 model that uses RL to generate adversarial code samples to test the vulnerabilities of programming language models. (2025) paper?