Bellman Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Schramm, Liam, Boularias, Abdeslam
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915590262751232
author Schramm, Liam
Boularias, Abdeslam
author_facet Schramm, Liam
Boularias, Abdeslam
contents Diffusion models have seen tremendous success as generative architectures. Recently, they have been shown to be effective at modelling policies for offline reinforcement learning and imitation learning. We explore using diffusion as a model class for the successor state measure (SSM) of a policy. We find that enforcing the Bellman flow constraints leads to a simple Bellman update on the diffusion step distribution.
format Preprint
id arxiv_https___arxiv_org_abs_2407_12163
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bellman Diffusion Models
Schramm, Liam
Boularias, Abdeslam
Machine Learning
Robotics
Diffusion models have seen tremendous success as generative architectures. Recently, they have been shown to be effective at modelling policies for offline reinforcement learning and imitation learning. We explore using diffusion as a model class for the successor state measure (SSM) of a policy. We find that enforcing the Bellman flow constraints leads to a simple Bellman update on the diffusion step distribution.
title Bellman Diffusion Models
topic Machine Learning
Robotics
url https://arxiv.org/abs/2407.12163