AI PAPERS/DAILY
Subscribe free Open sourceView on GitHub Star This project is open sourceRead the code or use it in your own project. If you like it, don’t forget to give it a ★ star on GitHub.

All papersOther MLUniversity of Geneva

Gaussian Distillation of Flow Policies

/ Paper arXiv 2610.40271

Key numbers

0.02%…a flow policy's final layer with a Gaussian readout trained on just 0.02% of eligible states

From the paperCopied from the abstract, not written by AI.

Abstract

From the paperThe authors' own words.

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.

From the full paper

From the paperCopied from the paper itself by our code.

Reading the paper on arXiv…

Ask this paper

/ Ask a questionAnswers come from the full paper and name the section

    / Your notes

    Select text in the abstract to highlight it or add a note. They stay in this browser.

      / Read next, same idea

      Read the PDF