Training vision-language-action (VLA) policies typically depends on substantial robot demonstration data, making human teleoperation a costly and cumbersome bottleneck, particularly for whole-body humanoid interaction. Reinforcement learning in simulation offers an alternative for scaling this data, but designing task-...
Kevin Park, Izat Rasyad, Dvij Kalaria et al.· 0 citations
Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integrate perception with control. We present Reconstruct, Practice, Go Real (RPG), a framework for autonomous improvement of robot execution systems without updating model wei...
Yen-Jen Wang, Hao-Zhe Jiang, Shu-Ying Deng et al.· 12 citations
Graph-as-Policy (GaP) is introduced, a multi-agent coding harness that generates directed computation graphs with perception, planning, and control nodes from a Modular Open Robot Skill Library (MORSL), and can achieve success rates that significantly outperform baselines.
Kai-Peng Chen, Shuang-Yu Xie, Letian Fu et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.