# CLEAR: Closed-Loop Reinforcement Learning at Scale for End-to-End Autonomous Driving Source: [CLEAR: Closed-Loop Reinforcement Learning at Scale for End-to-End Autonomous Driving]() Collection index: [llms.txt]() Data updated: 2026-07-08T05:00:04.941Z Authors: Yunxiao Shi, Hong Cai, Mohammad Ghavamzadeh, Fatih Porikli Published: 2026-07-03T00:34:50.000Z ## Abstract End-to-end autonomous driving (E2E-AD) aims to directly map raw sensor information to driving actions. Recently, with the rapid advancement of multi-modal large language models (MLLMs), researchers have proposed the paradigm of Vision-Language-Action (VLA) models for E2E-AD, where it seeks to integrate visual perception, language understanding and action prediction within a single policy. However, existing VLA-based policies largely adopts imitation learning, where it only learns to drive by optimizing distance-based metrics w.r.t. logged expert trajectories. Such distribution shift between open-loop training and closed-loop inference leads to suboptimal performance in closed-loop planning. To close this gap, we present CLEAR, a system that enables closed-loop training using Reinforcement Learning (RL) at scale for E2E-AD. We propose to learn a novel residual waypoint policy around the waypoint prior from pretrained VLA policies, effectively harnessing the knowledge within. On another front, one of the key challenges to scale up RL for vision-based policies is the number of parallel simulation environments since RL is data hungry. To that end, we design a heterogeneous pipeline that places the simulator and the VLA learner on distinct compute groups, which allows us to dramatically increase the number of simulation environments running in parallel while avoiding resource contention and maintaining training stability. We show that with a simple reward, CLEAR significantly outperforms previous methods and sets new state-of-the-art performance on the challenging benchmarks of CARLA longest6 v2 and Bench2Drive. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Closed-loop Planning on CARLA longest6 v2 (test)](): Closed-loop Planning; CARLA Longest6 v2 (test); DS Score: 39.89. - [Closed-loop Autonomous Driving Planning on Bench2Drive (test)](): Closed-loop Autonomous Driving Planning; Bench2Drive (test); Driving Score (DS): 86.8. ## Original sources and implementation [Original paper]() [PDF]()