arXiv Machine Learning July 3, 2026 By Sacha Morin, Moonsub Byeon, Alexia Jolicoeur-Martineau, S\'ebastien Lachapelle

On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning

Read the original on arXiv Machine Learning →

arXiv:2602. 02762v2 Announce Type: replace Abstract: Semi-supervised imitation learning (SSIL) consists in learning a policy from a small dataset of action-labeled trajectories and a much larger dataset of action-free trajectories.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

benchmarks

arXiv Machine Learning

Jun 25

ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning

arXiv:2501. 14622v5 Announce Type: replace Abstract: Learning efficient representations for decision-making policies is a challenge in imitation learning (IL).

By Aleksandar Vujinovic, Aleksandar Kovacevic

rag diffusion

arXiv AI

Jun 9

Difference-Aware Retrieval Policies for Imitation Learning

arXiv:2606. 09758v1 Announce Type: cross Abstract: Parametric imitation learning via behavior cloning can suffer from poor generalization to out-of-distribution states due to compounding errors during deployment.

By Quinn Pfeifer, Ethan Pronovost, Paarth Shah, Khimya Khetarpal, Siddhartha Srinivasa, Abhishek Gupta

robotics

arXiv AI

2d ago

TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models

arXiv:2610.00899v1 Announce Type: cross Abstract: Autoregressive Vision-Language-Action models often represent continuous robot actions as discrete token sequences, enabling action prediction with st...

By Keisuke Shirai, Tomohiro Motoda, Hanbit Oh, Ryoichi Nakajo, Roman Mykhailyshyn, Ryo Hanai, Shotaro Miwa, Yukiyasu Domae

nlp robotics efficiency multimodal

arXiv Machine Learning

Jul 31

CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations

arXiv:2505. 04999v2 Announce Type: replace-cross Abstract: Learning robot control policies from demonstrations typically requires action-labeled expert data, which is expensive to collect through teleoperation.

By Anthony Liang, Pavel Czempin, Matthew M. Hong, Yutai Zhou, Jingzhen Wang, Erdem Biyik, Stephen Tu

robotics

arXiv AI

Jul 7

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching

arXiv:2603. 27044v3 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) is widely recognized as sample-inefficient, a limitation attributable in part to the high dimensionality and substantial functional redundancy inherent to the policy parameter space.

By Andrea Fraschini, Davide Tenedini, Riccardo Zamboni, Mirco Mutti, Marcello Restelli

diffusion reinforcement-learning benchmarks

arXiv Computer Vision

4d ago

RoXDrive: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving via Action-Faithful Rollouts

arXiv:2609.36851v1 Announce Type: new Abstract: End-to-end autonomous driving policies are commonly trained via imitation learning on logged demonstrations without observing the consequences of their...

By Hongbin Lin, Chaoda Zheng, Yiming Yang, Xiangyu Li, Shijia Chen, Jinhao Deng, Kangjie Chen, Dongbin Zhang, Jie Feng, Yu Zhang, Xianming Liu, Shuguang Cui, Boyang Wang, Zhen Li

agents reinforcement-learning robotics safety

One email a morning, machine-written

Related stories

ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning

Difference-Aware Retrieval Policies for Imitation Learning

TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models

CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching

RoXDrive: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving via Action-Faithful Rollouts