mlsanityData to 7 Oct 2026

Reinforcement learning for driving

269 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: reinforcement, reinforcement learning, driving, autonomous, policy

Key facts. Reinforcement learning for driving: 269 papers on arXiv since 2021 (data through 7 Oct 2026). 26 of its 269 mapped papers (10%) cite “MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning” (2021, arXiv 2109.12674). 23 of its 269 mapped papers (9%) cite “A Survey of Deep RL and IL for Autonomous Driving Policy Learning” (2021, arXiv 2101.01993). 3 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

3 new since 17 Sep

  1. Meta-Multi-Agent Reinforcement Learning for Fast Adaptation of Interactive Policies with Applications to Autonomous Driving also fits: Cooperative and V2X driving
  2. Brain-SAD: A Brain-Inspired Safe Autonomous Driving Control Framework with Dynamic Fear-Oriented Constraint on Dual-Policy
  3. Sometimes You Gotta Run Before You Can Walk: Run-then-Walk Scheduling Strategy for VLM Autonomous Driving also fits: Imitation-learning end-to-end planners

Foundations

Most cited by papers here

  1. MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning2021cited by 26 here
  2. A Survey of Deep RL and IL for Autonomous Driving Policy Learning2021cited by 23 here
  3. Efficient Deep Reinforcement Learning with Imitative Expert Priors for Autonomous Driving2021cited by 12 here
  4. Improved Deep Reinforcement Learning with Expert Demonstrations for Urban Autonomous Driving2021cited by 11 here
  5. Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization2022cited by 11 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021End-to-end Interpretable Neural Motion Plannercited by 6 here
  2. 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coachcited by 19 here
  3. 2022Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarioscited by 17 here
  4. 2023Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priorscited by 7 here
  5. 2024A Review of Reward Functions for Reinforcement Learning in the context of Autonomous Drivingcited by 7 here
19 more it builds on, not in this chain
  1. 2021A Survey of Deep RL and IL for Autonomous Driving Policy Learningcited by 23 here
  2. 2021Improved Deep Reinforcement Learning with Expert Demonstrations for Urban Autonomous Drivingcited by 11 here
  3. 2021Efficient Deep Reinforcement Learning with Imitative Expert Priors for Autonomous Drivingcited by 12 here
  4. 2021Human-in-the-Loop Deep Reinforcement Learning with Application to Autonomous Drivingcited by 7 here
  5. 2021Multi-Modal Fusion Transformer for End-to-End Autonomous Drivingcited by 9 here
  6. 2021Reward (Mis)design for Autonomous Drivingcited by 10 here
  7. 2021Learning to drive from a world on railscited by 11 here
  8. 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclescited by 10 here
  9. 2021Prioritized Experience-based Reinforcement Learning with Human Guidance for Autonomous Drivingcited by 7 here
  10. 2021MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learningcited by 26 here
  11. 2021Safe Driving via Expert Guided Policy Optimizationcited by 7 here
  12. 2022Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racingcited by 7 here
  13. 2022Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimizationcited by 11 here
  14. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 12 here
  15. 2022State Dropout-Based Curriculum Reinforcement Learning for Self-Driving at Unsignalized Intersectionscited by 8 here
  16. 2022Augmenting Reinforcement Learning with Transformer-based Scene Representation Learning for Decision-making of Autonomous Drivingcited by 6 here
  17. 2023Motion Planning for Autonomous Driving: The State of the Art and Future Perspectivescited by 6 here
  18. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 20 here
  19. 2023Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Researchcited by 7 here

The 24 most cited of 294.

Browse

30 of 269, ranked 6–35

  1. 6Reward (Mis)design for Autonomous Driving202110
  2. 7State Dropout-Based Curriculum Reinforcement Learning for Self-Driving at Unsignalized Intersections20228
  3. 8A Review of Reward Functions for Reinforcement Learning in the context of Autonomous Driving20247
  4. 9Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors20237
  5. 10Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racing20227
  6. 11Human-in-the-Loop Deep Reinforcement Learning with Application to Autonomous Driving20217
  7. 12Prioritized Experience-based Reinforcement Learning with Human Guidance for Autonomous Driving20217
  8. 13Safe Driving via Expert Guided Policy Optimization20217
  9. 14HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving20246
  10. 15Augmenting Reinforcement Learning with Transformer-based Scene Representation Learning for Decision-making of Autonomous Driving20226
All 30
  1. 16Accelerating Reinforcement Learning for Autonomous Driving using Task-Agnostic and Ego-Centric Motion Skills20225
  2. 17Reinforcement Learning from Simulation to Real World Autonomous Driving using Digital Twin20225
  3. 18A Safe Hierarchical Planning Framework for Complex Driving Scenarios based on Reinforcement Learning20215
  4. 19Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Driving20215
  5. 20DQ-GAT: Towards Safe and Efficient Autonomous Driving with Deep Q-Learning and Graph Attention Networks20215
  6. 21GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving20215
  7. 22Autonomous Driving at Unsignalized Intersections: A Review of Decision-Making Challenges and Reinforcement Learning-Based Solutions20244
  8. 23Identify, Estimate and Bound the Uncertainty of Reinforcement Learning for Autonomous Driving20234
  9. 24Action and Trajectory Planning for Urban Autonomous Driving with Hierarchical Reinforcement Learning20234
  10. 25Safety-aware Causal Representation for Trustworthy Offline Reinforcement Learning in Autonomous Driving20234
  11. 26Tackling Real-World Autonomous Driving using Deep Reinforcement Learning20224
  12. 27Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning20214
  13. 28Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement20214
  14. 29Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Driving20253
  15. 30FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing20233
  16. 31Risk-Aware Reward Shaping of Reinforcement Learning Agents for Autonomous Driving20233
  17. 32How to Learn from Risk: Explicit Risk-Utility Reinforcement Learning for Efficient and Safe Driving Strategies20223
  18. 33Hierarchical Program-Triggered Reinforcement Learning Agents For Automated Driving20213
  19. 34Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning20213
  20. 35Modified DDPG car-following model with a real-world human driving experience with CARLA simulator20213