mlsanityData to 7 Oct 2026

Good Data Is All Imitation Learning Needs

arXiv 2409.17605 ↗First posted 26 Sep 2024cs.CV cs.LGcited by 2

On the map: Offline RL and imitation learning from data → Imitation and offline RL for driving

Abstract (arXiv)

In this paper, we address the limitations of traditional teacher-student models, imitation learning, and behaviour cloning in the context of Autonomous/Automated Driving Systems (ADS), where these methods often struggle with incomplete coverage of real-world scenarios. To enhance the robustness of such models, we introduce the use of Counterfactual Explanations (CFEs) as a novel data augmentation technique for end-to-end ADS. CFEs, by generating training samples near decision boundaries through minimal input modifications, lead to a more comprehensive representation of expert driver strategies, particularly in safety-critical scenarios. This approach can therefore help improve the model's ability to handle rare and challenging driving events, such as anticipating darting out pedestrians, ultimately leading to safer and more trustworthy decision-making for ADS. Our experiments in the CARLA simulator demonstrate that CF-Driver outperforms the current state-of-the-art method, achieving a higher driving score and lower infraction rates. Specifically, CF-Driver attains a driving score of 84.2, surpassing the previous best model by 15.02 percentage points. These results highlight the effectiveness of incorporating CFEs in training end-to-end ADS. To foster further research, the CF-Driver code is made publicly available.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Imitation and offline RL for driving, one of 13 directions in Offline RL and imitation learning from data. Builds on 36 of its 45 references that are in the map. First posted on arXiv 26 Sep 2024.

Builds on

36 of 45 references.

References · 36

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  3. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  4. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  5. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 769
  6. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  7. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
  8. 2021Multi-Modal Fusion Transformer for End-to-End Autonomous Drivingcited by 372
  9. 2019Learning by Cheatingcited by 361
  10. 2019Counterfactual Visual Explanationscited by 312
  11. 2022Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformercited by 211
  12. 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coachcited by 191
24 more
  1. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  2. 2020Multi-Objective Counterfactual Explanationscited by 157
  3. 2019Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifierscited by 143
  4. 2023DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Drivingcited by 142
  5. 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
  6. 2021Learning to drive from a world on railscited by 114
  7. 2018CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-drivingcited by 96
  8. 2023ReasonNet: End-to-End Driving with Temporal and Global Reasoningcited by 92
  9. 2023Data Quality in Imitation Learningcited by 72
  10. 2020Learning What Makes a Difference from Counterfactual Examples and Gradient Supervisioncited by 66
  11. 2019Uncertainty Quantification with Statistical Guarantees in End-to-End Autonomous Driving Controlcited by 60
  12. 2021An Investigation of the (In)effectiveness of Counterfactually Augmented Datacited by 42
  13. 2021STEEX: Steering Counterfactual Explanations with Semanticscited by 40
  14. 2024JUICER: Data-Efficient Imitation Learning for Robotic Assemblycited by 36
  15. 2022ROAD-R: The Autonomous Driving Dataset with Logical Requirementscited by 34
  16. 2019Why Does My Model Fail? Contrastive Local Explanations for Retail Forecastingcited by 31
  17. 2019Counterfactual Explanation Algorithms for Behavioral and Textual Datacited by 26
  18. 2023Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learningcited by 10
  19. 2017Burn-In Demonstrations for Multi-Modal Imitation Learningcited by 9
  20. 2024SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policiescited by 8
  21. 2023Offline Imitation Learning with Variational Counterfactual Reasoningcited by 7
  22. 2023SAFE: Saliency-Aware Counterfactual Explanations for DNN-based Automated Driving Systemscited by 5
  23. 2024Taming Transformers for Realistic Lidar Point Cloud Generationcited by 5
  24. 2023Counterfactual Explainer Framework for Deep Reinforcement Learning Models Using Policy Distillationcited by 3

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulatorscited by 34
  2. 2025Bootstrapping Imitation Learning for Long-horizon Manipulation via Hierarchical Data Collection Spacecited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2022Learning from Demonstrations of Critical Driving Behaviours Using Driver's Risk Field
  2. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst
  3. 2025Learning to Drive by Imitating Surrounding Vehicles
  4. 2025LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
  5. 2025From Imitation to Optimization: A Comparative Study of Offline Learning for Autonomous Driving
  6. 2022Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios
  7. 2024IGDrivSim: A Benchmark for the Imitation Gap in Autonomous Driving
  8. 2019Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation