新论文 · v1arXiv:2610.40271
Gaussian Distillation of Flow Policies
Youssef Saied, Ziyad Sheebaelhamd, Claire Vernade, François Fleuret
Flow policies are among the strongest robot controllers and are well suited to modelling multimodal action distributions. Our analysis shows that the continuous-action distributions of the studied flow policies are well approximated by Gaussians. We propose the Gaussian Action Readout (GAR), which replaces a flow policy's final layer with a Gaussian readout trained on just 0.02% of eligible states, while keeping the rest of the network frozen. It samples with one action-network pass, gives closed-form likelihoods, and achieves near-teacher task success at up to twice the inference speed.
尚无 AI 解读，展示原文摘要
cs.RO