2026
π∗0.6π0.6∗\pi^{*}_{0.6}: a VLA That Learns From Experience
RSS 2026poster
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) …