# Reinforcement learning for driving

Area: [End-to-end autonomous driving](https://mlsanity.com/driving/index.md). HTML: https://mlsanity.com/driving/reinforcement-learning-for-driving/

## Key facts

- Reinforcement learning for driving: 269 papers on arXiv since 2021 (data through 14 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).
- 6 new papers 17 Sep–14 Oct.

## Most cited here

- [MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning](https://mlsanity.com/paper/2109.12674/) (2021), cited by 26 papers here
- [A Survey of Deep RL and IL for Autonomous Driving Policy Learning](https://mlsanity.com/paper/2101.01993/) (2021), cited by 23 papers here
- [Efficient Deep Reinforcement Learning with Imitative Expert Priors for Autonomous Driving](https://mlsanity.com/paper/2103.10690/) (2021), cited by 12 papers here
- [Improved Deep Reinforcement Learning with Expert Demonstrations for Urban Autonomous Driving](https://mlsanity.com/paper/2102.09243/) (2021), cited by 11 papers here
- [Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization](https://mlsanity.com/paper/2202.10341/) (2022), cited by 11 papers here
- [Reward (Mis)design for Autonomous Driving](https://mlsanity.com/paper/2104.13906/) (2021), cited by 10 papers here
- [State Dropout-Based Curriculum Reinforcement Learning for Self-Driving at Unsignalized Intersections](https://mlsanity.com/paper/2207.04361/) (2022), cited by 8 papers here
- [Human-in-the-Loop Deep Reinforcement Learning with Application to Autonomous Driving](https://mlsanity.com/paper/2104.07246/) (2021), cited by 7 papers here
- [Prioritized Experience-based Reinforcement Learning with Human Guidance for Autonomous Driving](https://mlsanity.com/paper/2109.12516/) (2021), cited by 7 papers here
- [Safe Driving via Expert Guided Policy Optimization](https://mlsanity.com/paper/2110.06831/) (2021), cited by 7 papers here

## New (17 Sep–14 Oct)

- [Race to Recovery: Designing Advanced Safety Systems for Autonomous Driving via Learning Autonomous Racing](https://mlsanity.com/paper/2610.20873/) (2026-10-14)
- [Comprehensive Comparisons of Reinforcement Learning Algorithms in Autonomous Driving](https://mlsanity.com/paper/2610.19429/) (2026-10-14)
- [Beyond Safe Execution: Safe Online Reinforcement Learning for Autonomous Driving with Value Calibration and Adaptive Guidance](https://mlsanity.com/paper/2610.17799/) (2026-10-13)
- [Meta-Multi-Agent Reinforcement Learning for Fast Adaptation of Interactive Policies with Applications to Autonomous Driving](https://mlsanity.com/paper/2610.00705/) (2026-09-30)
- [Brain-SAD: A Brain-Inspired Safe Autonomous Driving Control Framework with Dynamic Fear-Oriented Constraint on Dual-Policy](https://mlsanity.com/paper/2609.38016/) (2026-09-29)
- [Sometimes You Gotta Run Before You Can Walk: Run-then-Walk Scheduling Strategy for VLM Autonomous Driving](https://mlsanity.com/paper/2609.25831/) (2026-09-22)