State-Action Inpainting Diffuser for Continuous Control with Delay

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Han, Dongqi, Wang, Wei, Zhang, Enze, Li, Dongsheng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912937090744320
author Han, Dongqi
Wang, Wei
Zhang, Enze
Li, Dongsheng
author_facet Han, Dongqi
Wang, Wei
Zhang, Enze
Li, Dongsheng
contents Signal delay poses a fundamental challenge in continuous control and reinforcement learning (RL) by introducing a temporal gap between interaction and perception. Current solutions have largely evolved along two distinct paradigms: model-free approaches which utilize state augmentation to preserve Markovian properties, and model-based methods which focus on inferring latent beliefs via dynamics modeling. In this paper, we bridge these perspectives by introducing State-Action Inpainting Diffuser (SAID), a framework that integrates the inductive bias of dynamics learning with the direct decision-making capability of policy optimization. By formulating the problem as a joint sequence inpainting task, SAID implicitly captures environmental dynamics while directly generating consistent plans, effectively operating at the intersection of model-based and model-free paradigms. Crucially, this generative formulation allows SAID to be seamlessly applied to both online and offline RL. Extensive experiments on delayed continuous control benchmarks demonstrate that SAID achieves state-of-the-art and robust performance. Our study suggests a new methodology to advance the field of RL with delay.
format Preprint
id arxiv_https___arxiv_org_abs_2603_01553
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle State-Action Inpainting Diffuser for Continuous Control with Delay
Han, Dongqi
Wang, Wei
Zhang, Enze
Li, Dongsheng
Artificial Intelligence
Machine Learning
Signal delay poses a fundamental challenge in continuous control and reinforcement learning (RL) by introducing a temporal gap between interaction and perception. Current solutions have largely evolved along two distinct paradigms: model-free approaches which utilize state augmentation to preserve Markovian properties, and model-based methods which focus on inferring latent beliefs via dynamics modeling. In this paper, we bridge these perspectives by introducing State-Action Inpainting Diffuser (SAID), a framework that integrates the inductive bias of dynamics learning with the direct decision-making capability of policy optimization. By formulating the problem as a joint sequence inpainting task, SAID implicitly captures environmental dynamics while directly generating consistent plans, effectively operating at the intersection of model-based and model-free paradigms. Crucially, this generative formulation allows SAID to be seamlessly applied to both online and offline RL. Extensive experiments on delayed continuous control benchmarks demonstrate that SAID achieves state-of-the-art and robust performance. Our study suggests a new methodology to advance the field of RL with delay.
title State-Action Inpainting Diffuser for Continuous Control with Delay
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2603.01553