arXiv Machine Learning By Lehong Wu, Yuxiao Qu, Zheyuan Hu, Ivan Zhang, Limin Wei, Zackory Erickson, Aviral Kumar

$R^3$: Training Robots to Reason in Natural Language via Reinforcement Learning

Read the original on arXiv Machine Learning →

The paper introduces $R^3$, a post‑training method that converts vision‑language models into robotic reasoners by first mid‑training on expert reasoning traces and then refining them with single‑step rubric‑based reinforcement learning. $R^3$ enables free‑form language reasoning to guide low‑level manipulation policies, improving exploration, generalization, and performance on long‑horizon tasks in Language Table and simulated bimanual grocery packing benchmarks. The approach outperforms instruction‑only imitation learning baselines and demonstrates that natural language reasoning can serve as a test‑time compute mechanism for steering robotic actions.

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.

arXiv AI
Jun 2

From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models

arXiv:2606. 00083v1 Announce Type: cross Abstract: Reinforcement learning relies on accurate reward functions, which are often hand-crafted or even unavailable in real-world applications, such as robotics.

By Christian Gumbsch, Leonardo Barcellona, Lennard Sch\"unemann, Platon Karageorgis, Andrii Zadaianchuk, Zehao Wang, Sergey Zakharov, Fabien Despinoy, Rahaf Aljundi, Efstratios Gavves
arXiv AI
Jul 28

A Few Words Go a Long Way: Language Guided Robot Policy Synthesis

arXiv:2607. 23784v1 Announce Type: cross Abstract: While vision-language-action models have demonstrated impressive zero-shot manipulation capabilities, they remain fundamentally black box policies that are difficult to interpret, adapt, or correct when they inevitably fail.

By Daphne Chen, Archit Ritesh Jain, Eric Goossen, Emma Romig, Michael Murray, Nick Walker, Maya Cakmak