$R^3$: Training Robots to Reason in Natural Language via Reinforcement Learning
Reasoning in language allows foundation models to spend more test-time compute on hard problems, such as those requiring decomposition, constraint tracking, and prediction of future consequences. Whether this mechanism can improve robotic manipulation remains unclear, where long-horizon tasks require tracking partial progress, reasoning about object relations, recovering from mistakes, and…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
