mlsanityData to 7 Oct 2026

Imitation and offline RL for driving

226 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: driving, autonomous, autonomous driving, imitation, traffic

Key facts. Imitation and offline RL for driving: 226 papers on arXiv since 2018 (data through 7 Oct 2026). 33 of its 226 mapped papers (15%) cite “ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst” (2018, arXiv 1812.03079). 10 of its 226 mapped papers (4%) cite “Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios” (2022, arXiv 2212.11419). 3 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

3 new since 17 Sep

  1. RoXDrive: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving via Action-Faithful Rollouts
  2. Stability-Aware Imitation Learning from Model Predictive Control for Autonomous Vehicle Lateral Control: Exact Q-Loss and a Novel Training Procedure
  3. Learning Reliable Parking Policies via Offline Reinforcement Learning with Quantized Action Representations

Foundations

Most cited by papers here

  1. ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst2018cited by 33 here
  2. Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios2022cited by 10 here
  3. Deep Reinforcement Learning for Autonomous Driving: A Survey2020cited by 8 here
  4. Conditional Affordance Learning for Driving in Urban Environments2018cited by 7 here
  5. Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safety2019cited by 7 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 15 here
  2. 2020MOReL : Model-Based Offline Reinforcement Learningcited by 7 here
  3. 2020MOPO: Model-based Offline Policy Optimizationcited by 7 here
  4. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 11 here
  5. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 14 here
  6. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 11 here
18 more it builds on, not in this chain
  1. 2018Multi-Agent Imitation Learning for Driving Simulationcited by 5 here
  2. 2018Conditional Affordance Learning for Driving in Urban Environmentscited by 7 here
  3. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 9 here
  4. 2018Multi-Agent Generative Adversarial Imitation Learningcited by 5 here
  5. 2018Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learningcited by 5 here
  6. 2018An Algorithmic Perspective on Imitation Learningcited by 8 here
  7. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 33 here
  8. 2019Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safetycited by 7 here
  9. 2019Causal Confusion in Imitation Learningcited by 16 here
  10. 2019A Divergence Minimization Perspective on Imitation Learning Methodscited by 8 here
  11. 2019Urban Driving with Conditional Imitation Learningcited by 7 here
  12. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 8 here
  13. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 18 here
  14. 2020Efficient Sampling-Based Maximum Entropy Inverse Reinforcement Learning with Application to Autonomous Drivingcited by 6 here
  15. 2020Driving Behavior Modeling using Naturalistic Human Driving Data with Inverse Reinforcement Learningcited by 6 here
  16. 2022Model-Based Imitation Learning for Urban Drivingcited by 6 here
  17. 2022Hierarchical Model-Based Imitation Learning for Planning in Autonomous Drivingcited by 7 here
  18. 2022Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarioscited by 10 here

The 24 most cited of 246.

Browse

30 of 226, ranked 6–35

  1. 6Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving20227
  2. 7Urban Driving with Conditional Imitation Learning20197
  3. 8Model-Based Imitation Learning for Urban Driving20226
  4. 9Efficient Sampling-Based Maximum Entropy Inverse Reinforcement Learning with Application to Autonomous Driving20206
  5. 10Driving Behavior Modeling using Naturalistic Human Driving Data with Inverse Reinforcement Learning20206
  6. 11Conditional Predictive Behavior Planning with Inverse Reinforcement Learning for Human-like Autonomous Driving20225
  7. 12Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement20215
  8. 13Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning20195
  9. 14Driving with Style: Inverse Reinforcement Learning in General-Purpose Planning for Automated Driving20195
  10. 15Multi-Agent Imitation Learning for Driving Simulation20185
All 30
  1. 16Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning20185
  2. 17Modeling Human Driving Behavior through Generative Adversarial Imitation Learning20204
  3. 18Integrating kinematics and environment context into deep inverse reinforcement learning for predicting off-road vehicle trajectories20184
  4. 19CCIL: Context-conditioned imitation learning for urban driving20233
  5. 20Offline Reinforcement Learning for Road Traffic Control20223
  6. 21A deep inverse reinforcement learning approach to route choice modeling with context-dependent rewards20223
  7. 22Exploring Imitation Learning for Autonomous Driving with Feedback Synthesizer and Differentiable Rasterization20213
  8. 23UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning20213
  9. 24TrajGAIL: Generating Urban Vehicle Trajectories using Generative Adversarial Imitation Learning20203
  10. 25PILOT: Efficient Planning by Imitation Learning and Optimisation for Safe Autonomous Driving20203
  11. 26From Imitation to Optimization: A Comparative Study of Offline Learning for Autonomous Driving20252
  12. 27Addressing Limitations of State-Aware Imitation Learning for Autonomous Driving20232
  13. 28Safety-aware Causal Representation for Trustworthy Offline Reinforcement Learning in Autonomous Driving20232
  14. 29Driving in Real Life with Inverse Reinforcement Learning20222
  15. 30Multi-task Learning with Attention for End-to-end Autonomous Driving20212
  16. 31Objective-aware Traffic Simulation via Inverse Reinforcement Learning20212
  17. 32Adversarial Mixture Density Networks: Learning to Drive Safely from Collision Data20212
  18. 33Adversarial Imitation Learning via Random Search in Lane Change Decision-Making20212
  19. 34Generative Adversarial Imitation Learning for End-to-End Autonomous Driving on Urban Environments20212
  20. 35Imitation Learning of Hierarchical Driving Model: from Continuous Intention to Continuous Trajectory20202