Ali Amin, Raichelle Aniceto, Ashwin Balakrishna, Kevin Black, Ken Conley, Grace B. Connors, James Darpinian, Karan Dhabalia, Jared Di Carlo, Danny Driess, Michael Robert Equi, Adnan Esmail, Yunhao Fang, Chelsea Finn, Catherine Glossop, Thomas Godden, Ivan Goryachev, Lachy Groom, Hunter Hancock, Karol Hausman, Gashon Hussein, Brian Ichter, Szymon Jakubczak, Rowan Jen, Tim Jones, Benjamin Katz, Liyiming Ke, Chandra Kuchi, Marinda Lamb, Devin Leblanc, Sergey Levine, Adrian Li-Bell, Yao Lu, Vishnu Mano, Mohith Mothukuri, Suraj Nair, Karl Pertsch, Allen Z. Ren, Charvi Sharma, Lucy Xiaoyang Shi, Laura Smith, Jost Tobias Springenberg, Kyle Stachowicz, Will Stoeckle, Alexander Swerdlow, James Tanner, Marcel Torne, Quan Vuong, Anna Walling, Haohuan Wang, Blake Williams, Sukwon Yoo, Lili Yu, Ury Zhilinsky, Zhiyuan Zhou

Paper ID 87

Session VLA Models

Poster session details TBA

Abstract: Vision–language–action (VLA) models offer a promising path toward general-purpose robots, but achieving the reliability and speed required for practical deployment remains challenging. We present a general-purpose method, RL with Experience and Corrections via Advantage-conditioned Policies (RECAP) that improves the efficiency and reliability of VLA policies by utilizing their real-world experience. Our method introduces value-based advantage conditioning during both pre-training and post-training phases, enabling VLA policies to ingest highly heterogeneous real-world experience, including human demonstrations, policy rollouts, and online correction data. We show that the π0.6* model, trained with RECAP, achieves hours-long deployment of folding diverse laundry in real homes, can reliably assemble boxes in a factory, and make espresso drinks using a professional espresso machine. On some of the hardest tasks, RECAP more than doubles task throughput and roughly halves the task failure rate.


Back

Papers

Next