Planning Using Schrödinger Bridge Diffusion Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteur principal: Srivastava, Adarsh
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913396571504640
author Srivastava, Adarsh
author_facet Srivastava, Adarsh
contents Offline planning often struggles with poor sampling efficiency as it tries to learn policies from scratch. Especially with diffusion models, such cold start practices mean that both training and sampling become very expensive. We hypothesize that certain environment constraint priors or cheaply available policies make it unnecessary to learn from scratch, and explore a way to incorporate such priors in the learning process. To achieve that, we borrow a variation of the Schrödinger bridge formulation from the image-to-image setting and apply it to planning tasks. We study the performance on some planning tasks and compare the performance against the DDPM formulation. The code for this work is available at https://github.com/adrshsrvstv/bridge_diffusion_planning.
format Preprint
id arxiv_https___arxiv_org_abs_2406_12458
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Planning Using Schrödinger Bridge Diffusion Models
Srivastava, Adarsh
Robotics
Offline planning often struggles with poor sampling efficiency as it tries to learn policies from scratch. Especially with diffusion models, such cold start practices mean that both training and sampling become very expensive. We hypothesize that certain environment constraint priors or cheaply available policies make it unnecessary to learn from scratch, and explore a way to incorporate such priors in the learning process. To achieve that, we borrow a variation of the Schrödinger bridge formulation from the image-to-image setting and apply it to planning tasks. We study the performance on some planning tasks and compare the performance against the DDPM formulation. The code for this work is available at https://github.com/adrshsrvstv/bridge_diffusion_planning.
title Planning Using Schrödinger Bridge Diffusion Models
topic Robotics
url https://arxiv.org/abs/2406.12458