Back to papers
August 26, 2026cs.ROcs.AIcs.CLcs.LG

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

Lehong Wu, Yuxiao Qu, Zheyuan Hu, Ivan Zhang, Limin Wei, Zackory Erickson, Aviral Kumar
Read on arXivDownload PDF
Categories

cs.RO, cs.AI, cs.CL, cs.LG