RL for Autonomous Driving

RL: Reinforcement Learning

Overview

The field studies how vehicles can learn driving decisions and controls through rewards and interaction, including how to navigate traffic, avoid hazards, and coordinate with other road users. Methods range from PPO, SAC, and DQN to model-based and world-model learning, multi-agent reinforcement learning, and combinations of imitation learning with diffusion or vision-language-action planners. Safety is addressed through reward design, expert guidance, control barrier functions, and reachability constraints, with evaluation commonly using CARLA, nuPlan, NAVSIM, and Bench2Drive. A central challenge is achieving sample-efficient learning that remains safe and reliable in closed-loop, unfamiliar, and real-world conditions, where simulator fidelity and trade-offs among safety, progress, and comfort matter.

Latest papers

CardsList

131 papers15 papers in the last four weeks, down 6% on the four weeks before. 0.1% of all new papers.

  1. TSC: Topology-Conditioned Stackelberg Coordination for Multi-Agent Reinforcement Learning in Interactive Driving

    Feb 27, 2026Xiaotong Zhang, Gang Xiong, Yuanjing Wang +3Multi-Agent CoordinationDecentralized MARL

  2. DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Driving

    Feb 16, 2026Chenxu Dang, Sining Ang, Yongkang Li +7VLMs for Autonomous DrivingDiffusion-Based Planning

  3. Preference-Conditioned Multi-Objective Reinforcement Learning for Tactical Decision Making in Heavy-Duty Vehicles

    Jan 26, 2026Deepthi Pathare, Leo Laine, Morteza Haghir ChehreghaniMulti-Objective Reinforcement LearningRL for Autonomous Driving

  4. Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer

    Oct 28, 2025Zhenxin Li, Nadine Chang, Wenhao Yao +9Long-Tail Autonomous DrivingReinforcement Learning

  5. Drive As You Like: Multi-Head Diffusion with Reinforcement Learning for Personalized Driving

    Aug 23, 2025Ding Fan, Xuewen Luo, Hwa Hui Tew +3Autonomous Driving PlanningAutonomous Driving

  6. DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving

    Jul 5, 2025Ziying Song, Lin Liu, Hongyu Pan +7End-to-End Autonomous DrivingDiffusion-Based Planning

  7. A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective

    Mar 31, 2025Zhuoren Li, Guizhe Jin, Ran Yu +8Autonomous Driving PlanningRL for Autonomous Driving

  8. Does Knowledge About Perceptual Uncertainty Help an Agent in Automated Driving?

    Feb 17, 2025Natalie Grabowsky, Annika Mütze, Joshua Wendland +2Autonomous Driving PlanningRL for Autonomous Driving

  9. Fading Expert Guidance: Bridging Model-Based and Learning-Based Control for Abortable Autonomous Overtaking

    Aug 18, 2023Jinxiong Lu, Gokhan Alcan, Ville KyrkiAutonomous Driving PlanningRL for Autonomous Driving

  10. Security of Deep Reinforcement Learning for Autonomous Driving: A Survey

    Dec 12, 2022Ambra Demontis, Srishti Gupta, Maura Pintor +6Robust RLRL for Autonomous Driving