mlsanityData to 14 Oct 2026

CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving

arXiv 2510.12560 ↗First posted 14 Oct 2025cs.CV cs.LG cs.ROcited by 0

On the map: World models → World models for autonomous driving

also in 3 more
Abstract (arXiv)

End-to-end autonomous driving models trained with imitation learning (IL) often generalize poorly, particularly in long-tail scenarios where expert demonstrations are sparse. Reinforcement learning (RL) can provide complementary task-level supervision, but applying RL to real-world autonomous driving is challenging in offline settings without interactive simulators, where datasets are dominated by expert actions and provide limited behavioral diversity. We propose CoIRL-AD, a competitive dual-policy framework that integrates IL and RL under a unified offline training regime. CoIRL-AD decouples imitation and reward optimization into separate actors to alleviate objective conflicts, uses imagined future rollouts for long-horizon reward estimation, and introduces a competition mechanism that selectively transfers beneficial behaviors while keeping RL anchored to expert-like driving. Experiments on the nuScenes benchmark show that CoIRL-AD consistently improves robustness over strong IL-based baselines, with especially large gains in cross-city generalization and long-tail scenarios. Code is available at: https://github.com/SEU-zxj/CoIRL-AD.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in World models for autonomous driving, one of 11 directions in World models. Builds on 33 of its 41 references that are in the map. First posted on arXiv 14 Oct 2025.

Builds on

33 of 41 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model1 Jul
  2. 2025End-to-End Driving with Online Trajectory Evaluation via BEV World Model2 Apr
  3. 2025AdaWM: Adaptive World Model based Planning for Autonomous Driving22 Jan
  4. 2024Imagine-2-Drive: Leveraging High-Fidelity World Models via Multi-Modal Diffusion Policies15 Nov
  5. 2024Navigation-Guided Sparse Scene Representation for End-to-End Autonomous Driving26 Sep
  6. 2024Enhancing End-to-End Autonomous Driving with Latent World Model12 Jun
  7. 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability27 May
  8. 2023Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving29 Nov

Other references · 25

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  5. 2023Mastering Diverse Domains through World Modelscited by 1,253
  6. 2022Planning-oriented Autonomous Drivingcited by 1,087
  7. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 622
  8. 2021Multi-Modal Fusion Transformer for End-to-End Autonomous Drivingcited by 377
  9. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planningcited by 289
  10. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuningcited by 260
  11. 2024Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillationcited by 249
  12. 2025LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RLcited by 248
13 more
  1. 2025ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Drivingcited by 198
  2. 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coachcited by 194
  3. 2023Panacea: Panoramic and Controllable Video Generation for Autonomous Drivingcited by 168
  4. 2022Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarioscited by 129
  5. 2025On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectificationcited by 127
  6. 2021Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradientscited by 122
  7. 2024Towards learning-based planning:The nuPlan benchmark for real-world autonomous drivingcited by 104
  8. 2025RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learningcited by 79
  9. 2024VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Drivingcited by 51
  10. 2024End-to-End Autonomous Driving without Costly Modularization and 3D Manual Annotationcited by 28
  11. 2025Learning Personalized Driving Styles via Reinforcement Learning from Human Feedbackcited by 17
  12. 2025Efficient Robotic Policy Learning via Latent Space Backward Planningcited by 14
  13. 2025IN-RIL: Interleaved Reinforcement and Imitation Learning for Policy Fine-Tuningcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving
  2. 2025From Imitation to Optimization: A Comparative Study of Offline Learning for Autonomous Driving
  3. 2025V-Max: A Reinforcement Learning Framework for Autonomous Driving
  4. 2025AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models
  5. 2024CIMRL: Combining IMitation and Reinforcement Learning for Safe Autonomous Driving
  6. 2019Decision Making for Autonomous Driving via Augmented Adversarial Inverse Reinforcement Learning
  7. 2025DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving
  8. 2026CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies