: Weights for the CaRL planner, which is noted as a top open-source RL planner for urban driving scenarios.
: The first public codebase for doing Reinforcement Learning with the CARLA autonomous driving simulator leaderboard. File: C.A.R.L.v1.0.zip ...
: 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 : Weights for the CaRL planner, which is
: Code for popular CARLA planners including Roach, PlanT, and Think2Drive. Alternative Possibilities If the file relates to a different field, it may refer to: (2025) paper
: A 2026 model that uses RL to generate adversarial code samples to test the vulnerabilities of programming language models. (2025) paper?
: A 2025 framework designed to improve Large Language Models' adherence to task constraints in planning problems like "BlocksWorld" and "TravelPlanner".