Projects

Policy Diffusion: Generative Models for Policy Datasets

A figure showing a humanoid controlled by a sequence of policies, beginning with “slide forward on your right foot while kicking with your left foot” (top left), then “run forward on left foot while dragging right foot”, then “quickly shuffle forward on your left foot”, and finally “wildly hop forward on left foot while lifting your right foot up”.

We show how to train a generative model over neural network parameters (a "diffusion graph hyper-network"). The resulting model is able to take in a task description (e.g. "hop forward on your right foot"), and produces a small neural network that performs that behavior. [ArXiv URL]

Large Language Models
Diffusion
Hyper-Networks
Authors:

This page is a stub. Please see the links above for more information.