mlsanityData to 14 Oct 2026

GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving

arXiv 2111.08575 ↗First posted 16 Nov 2021cs.RO cs.CVcited by 60

On the map: End-to-end autonomous driving → Reinforcement learning for driving

Abstract (arXiv)

Deep reinforcement learning (DRL) has been demonstrated to be effective for several complex decision-making applications such as autonomous driving and robotics. However, DRL is notoriously limited by its high sample complexity and its lack of stability. Prior knowledge, e.g. as expert demonstrations, is often available but challenging to leverage to mitigate these issues. In this paper, we propose General Reinforced Imitation (GRI), a novel method which combines benefits from exploration and expert data and is straightforward to implement over any off-policy RL algorithm. We make one simplifying hypothesis: expert demonstrations can be seen as perfect data whose underlying policy gets a constant high reward. Based on this assumption, GRI introduces the notion of offline demonstration agents. This agent sends expert data which are processed both concurrently and indistinguishably with the experiences coming from the online RL exploration agent. We show that our approach enables major improvements on vision-based autonomous driving in urban environments. We further validate the GRI method on Mujoco continuous control tasks with different off-policy RL algorithms. Our method ranked first on the CARLA Leaderboard and outperforms World on Rails, the previous state-of-the-art, by 17%.

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving. Builds on 28 of its 35 references that are in the map. First posted on arXiv 16 Nov 2021.

Builds on

28 of 35 references.

References · 28

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  4. 2015Continuous control with deep reinforcement learningcited by 3,407
  5. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  6. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  7. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  8. 2016End to End Learning for Self-Driving Carscited by 1,009
  9. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
  10. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 715
  11. 2018An Algorithmic Perspective on Imitation Learningcited by 459
  12. 2019Learning by Cheatingcited by 383
16 more
  1. 2021Multi-Modal Fusion Transformer for End-to-End Autonomous Drivingcited by 377
  2. 2018Implicit Quantile Networks for Distributional Reinforcement Learningcited by 369
  3. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 346
  4. 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coachcited by 194
  5. 2019End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordancescited by 149
  6. 2021Learning to drive from a world on railscited by 114
  7. 2017Neural Task Programming: Learning to Generalize Across Hierarchical Taskscited by 76
  8. 2018Reinforcement Learning from Imperfect Demonstrationscited by 75
  9. 2019ChainerRL: A Deep Reinforcement Learning Librarycited by 51
  10. 2019SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigationcited by 29
  11. 2017Deep Q-learning from Demonstrationscited by 28
  12. 2019SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewardscited by 28
  13. 2021Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Drivingcited by 22
  14. 2019Is Deep Reinforcement Learning Really Superhuman on Atari? Leveling the playing fieldcited by 15
  15. 2018End to End Vehicle Lateral Control Using a Single Fisheye Cameracited by 13
  16. 2021Learning from demonstrations with SACR2: Soft Actor-Critic with Reward Relabelingcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 10; 2023: 13; 2024: 12; 2025: 17; 2026: 8.

60 papers.

Sort:

By area:

  1. 2022Planning-oriented Autonomous Drivingcited by 1,087
  2. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 622
  3. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
  4. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Modelscited by 490
  5. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 485
  6. 2022ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learningcited by 368
  7. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planningcited by 289
  8. 2022Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baselinecited by 248
  9. 2024EMMA: End-to-End Multimodal Model for Autonomous Drivingcited by 231
  10. 2022Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformercited by 212
  11. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Drivingcited by 169
  12. 2022Learning from All Vehiclescited by 135
38 more
  1. 2023Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Surveycited by 103
  2. 2023ReasonNet: End-to-End Driving with Temporal and Global Reasoningcited by 93
  3. 2024RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Modelcited by 92
  4. 2025RAP: 3D Rasterization Augmented End-to-End Planningcited by 41
  5. 2025DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Drivingcited by 39
  6. 2025HiP-AD: Hierarchical and Multi-Granularity Planning with Deformable Attention for Autonomous Driving in a Single Decodercited by 35
  7. 2025CaRL: Learning Scalable Planning Policies with Simple Rewardscited by 35
  8. 2023PPAD: Iterative Interactions of Prediction and Planning for End-to-end Autonomous Drivingcited by 33
  9. 2025Vision-Language-Action Models for Autonomous Driving: Past, Present, and Futurecited by 33
  10. 2024Towards Collaborative Autonomous Driving: Simulation Platform and End-to-End Systemcited by 20
  11. 2023Coaching a Teachable Studentcited by 19
  12. 2022MMFN: Multi-Modal-Fusion-Net for End-to-End Drivingcited by 17
  13. 2024Prompting Multi-Modal Tokens to Enhance End-to-End Autonomous Driving Imitation Learning with LLMscited by 13
  14. 2024Autonomous Driving with Spiking Neural Networkscited by 13
  15. 2025Unraveling the Effects of Synthetic Data on End-to-End Autonomous Drivingcited by 12
  16. 2025AdaDrive: Self-Adaptive Slow-Fast System for Language-Grounded Autonomous Drivingcited by 10
  17. 2022Exploiting map information for self-supervised learning in motion forecastingcited by 8
  18. 2025A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulatorcited by 7
  19. 2025CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Modelcited by 7
  20. 2025FutureX: Enhance End-to-End Autonomous Driving via Latent Chain-of-Thought World Modelcited by 7
  21. 2025VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-grounded Autonomous Drivingcited by 6
  22. 2023An Invitation to Deep Reinforcement Learningcited by 5
  23. 2024Enhance Planning with Physics-informed Safety Controller for End-to-end Autonomous Drivingcited by 5
  24. 2025LeAD: The LLM Enhanced Planning System Converged with End-to-end Autonomous Drivingcited by 5
  25. 2023RLAD: Reinforcement Learning from Pixels for Autonomous Driving in Urban Environmentscited by 4
  26. 2025Interpretable Decision-Making for End-to-End Autonomous Drivingcited by 4
  27. 2025Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Drivingcited by 4
  28. 2026Scaling Self-Play for End-to-End Drivingcited by 4
  29. 2023Addressing Limitations of State-Aware Imitation Learning for Autonomous Drivingcited by 3
  30. 2024MaskFuser: Masked Fusion of Joint Multi-Modal Tokenization for End-to-End Autonomous Drivingcited by 3
  31. 2026Found-RL: foundation model-enhanced reinforcement learning for autonomous drivingcited by 3
  32. 2022DeFIX: Detecting and Fixing Failure Scenarios with Reinforcement Learning in Imitation Learning Based Autonomous Drivingcited by 2
  33. 2023Target-point Attention Transformer: A novel trajectory predict network for end-to-end autonomous drivingcited by 2
  34. 2023Combating the effects of speed and delays in end-to-end self-drivingcited by 2
  35. 2024Physics-informed Imitative Reinforcement Learning for Real-world Drivingcited by 2
  36. 2025Embodied Cognition Augmented End2End Autonomous Drivingcited by 2
  37. 2022STIR2: Reward Relabelling for combined Reinforcement and Imitation Learning on sparse-reward taskscited by 1
  38. 2023PaaS: Planning as a Service for reactive driving in CARLA Leaderboardcited by 1

50 most cited of 60 All 60 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2021Improved Deep Reinforcement Learning with Expert Demonstrations for Urban Autonomous Driving
  2. 2021Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning
  3. 2020Deep Reinforcement Learning for Autonomous Driving: A Survey
  4. 2025Pseudo-Expert Regularized Offline RL for End-to-End Autonomous Driving in Photorealistic Closed-Loop Environments
  5. 2024From Imitation to Exploration: End-to-end Autonomous Driving based on World Model
  6. 2021Efficient Deep Reinforcement Learning with Imitative Expert Priors for Autonomous Driving
  7. 2019Model-free Deep Reinforcement Learning for Urban Autonomous Driving
  8. 2020Guided Policy Search Model-based Reinforcement Learning for Urban Autonomous Driving