: 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
: CaRL: Learning Scalable Planning Policies with Simple Rewards File: C.A.R.L.v1.0.zip ...
: Proceedings of the Conference on Robot Learning (CoRL), 2025 : The paper introduces CaRL , a reinforcement
The zip file typically contains the codebase and pre-trained weights for the following: : The paper introduces CaRL
: Weights for the CaRL planner, which is noted as a top open-source RL planner for urban driving scenarios.
: Bernhard Jaeger, Daniel Dauner, Jens Beißwenger, Simon Gerstenecker, Kashyap Chitta, and Andreas Geiger
: 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
: CaRL: Learning Scalable Planning Policies with Simple Rewards
: Proceedings of the Conference on Robot Learning (CoRL), 2025
The zip file typically contains the codebase and pre-trained weights for the following:
: Weights for the CaRL planner, which is noted as a top open-source RL planner for urban driving scenarios.
: Bernhard Jaeger, Daniel Dauner, Jens Beißwenger, Simon Gerstenecker, Kashyap Chitta, and Andreas Geiger