2026
Sample Efficient Full-Finetuning of Generative Control Policies
Sarvesh Patil, Mitsuhiko Nakamoto, Shashwat Saxena, Manan Agarwal, Giri Anantharaman, Cleah Winston +11
ICML 2026poster
Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning. Yet there remains substantial debate over how to sample efficiently fine-tune them via reinforcement learning. A prevailing view holds that fine-tun…