arXiv Machine Learning June 16, 2026 By Xiaoji Zheng, Ziyuan Yang, Yanhao Chen, Yuhang Peng, Yuanrong Tang, Gengyuan Liu, Bokui Chen, Jiangtao Gong

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

Read the original on arXiv Machine Learning →

arXiv:2510. 12560v2 Announce Type: replace-cross Abstract: End-to-end autonomous driving models trained with imitation learning (IL) often generalize poorly, particularly in long-tail scenarios where expert demonstrations are sparse.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Aug 10

Minimal Ingredients for Reward Assignment from Expert Demonstrations

arXiv:2506. 06793v2 Announce Type: replace-cross Abstract: Reward assignment from scarce demonstrations is a key challenge in both offline and online imitation learning.

By Zixuan Dong, Yumi Omori, Keith Ross

reinforcement-learning benchmarks safety

arXiv AI

Jul 15

TADPO: Reinforcement Learning Goes Off-road

arXiv:2603. 05995v2 Announce Type: replace-cross Abstract: Off-road autonomous driving poses significant challenges such as navigating unmapped, variable terrain with uncertain and diverse dynamics.

By Zhouchonghao Wu, Raymond Song, Vedant Mundheda, Luis E. Navarro-Serment, Christof Schoenborn, Jeff Schneider

agents reinforcement-learning robotics

arXiv AI

Aug 3

Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints

arXiv:2501. 04426v2 Announce Type: replace-cross Abstract: Offline diversity maximization under imitation constraints can transform demonstration data into a set of distinct behavioral policies, improving robustness to distribution shift without additional environment interaction.

By Pavel Kolev, Marin Vlastelica, Georg Martius

robotics benchmarks safety

arXiv AI

Jun 19

Human-like autonomy emerges from self-play and a pinch of human data

arXiv:2606. 19370v1 Announce Type: cross Abstract: Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data.

By Daphne Cornelisse, Julian Hunt, Zixu Zhang, Wa\"el Doulazmi, Kevin Joseph, Jaime Fern\'andez Fisac, Eugene Vinitsky

reinforcement-learning

Hugging Face Trending Papers

Jul 9

Post-Training in End-to-End Autonomous Driving

End-to-end models that map multimodal inputs directly to future trajectories/maneuvers have emerged as an increasingly prominent research paradigm in autonomous driving. This class of models includes both Vision-Language-Action models and trajectory-generative planners.

agents robotics multimodal safety

arXiv Machine Learning

6d ago

Adaptation of Generalist Robot Policies with Minimal Data

arXiv:2608. 11363v1 Announce Type: cross Abstract: A central goal in robot learning is to move beyond task-specific human data collection toward robots that improve through autonomous interaction.

By Shreyas Kowshik, Sreyas Venkataraman, Leo Wang, Niharika Pant, Max Simchowitz, Aviral Kumar

agents reinforcement-learning robotics

Related stories

Minimal Ingredients for Reward Assignment from Expert Demonstrations

TADPO: Reinforcement Learning Goes Off-road

Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints

Human-like autonomy emerges from self-play and a pinch of human data

Post-Training in End-to-End Autonomous Driving

Adaptation of Generalist Robot Policies with Minimal Data