# Enabling Stateful Behaviors for Diffusion-based Policy Learning

arXiv: https://arxiv.org/abs/2404.12539 · HTML: https://mlsanity.com/paper/2404.12539/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 18 Apr 2024.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Built on by (most cited first, 3 of 3)

- [Generative Image as Action Models](https://mlsanity.com/paper/2407.07875/) (2024)
- [Subconscious Robotic Imitation Learning](https://mlsanity.com/paper/2412.20368/) (2024)
- [Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs](https://mlsanity.com/paper/2606.01072/) (2026)

## Abstract (arXiv)

While imitation learning provides a simple and effective framework for policy learning, acquiring consistent actions during robot execution remains a challenging task. Existing approaches primarily focus on either modifying the action representation at data curation stage or altering the model itself, both of which do not fully address the scalability of consistent action generation. To overcome this limitation, we introduce the Diff-Control policy, which utilizes a diffusion-based model to learn the action representation from a state-space modeling viewpoint. We demonstrate that we can reduce diffusion-based policies' uncertainty by making it stateful through a Bayesian formulation facilitated by ControlNet, leading to improved robustness and success rates. Our experimental results demonstrate the significance of incorporating action statefulness in policy learning, where Diff-Control shows improved performance across various tasks. Specifically, Diff-Control achieves an average success rate of 72% and 84% on stateful and dynamic tasks, respectively. Project page: https://github.com/ir-lab/Diff-Control