A VLA that Learns from Experience
pi.website · 2,860 words · saved by 1 readers
A method for training our generalist policies with RL to improve success rate and throughput on real-world tasks.
A VLA that Learns from Experience π * 0.6 : a VLA that Learns from Experience Published November 17, 2025 Email research@physicalintelligence.company Ali Amin, Raichelle Aniceto, Ashwin Balakrishna, Kevin Black, Ken Conley, Grace Connors, James Darpinian, Karan Dhabalia, Jared DiCarlo, Danny Driess, Michael 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, Ben Katz, Liyiming Ke, Chandra Kuchi, Marinda Lamb, Devin LeBlanc, Sergey Levine
saved by
related reading
- π*0.6: a VLA That Learns From Experiencephysicalintelligence.company
- Precise Manipulation with Efficient Online RLpi.website
- A Steerable Model with Emergent Capabilitiespi.website
- A VLA with Open-World Generalizationpi.website
- State of Robot Learning, December 2025vedder.io
- pistar06.pdfpi.website
- A VLA with Open-World Generalizationphysicalintelligence.company
- Emergence of Human to Robot Transfer in Vision-Language-Action Modelspi.website
- Physical Intelligence (π)pi.website
- SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningalphaxiv.org
- Stop Simulating, Start Experiencingpaoloai.substack.com
- $π_0$: A Vision-Language-Action Flow Model for General Robot Controlalphaxiv.org