State-Action Inpainting Diffuser for Continuous Control with Delay
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |