# Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Training

arXiv: https://arxiv.org/abs/2509.19752 · HTML: https://mlsanity.com/paper/2509.19752/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models.
- Builds on 28 of its 32 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)
- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 28 of 28)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [Diffusion Policy Policy Optimization](https://mlsanity.com/paper/2409.00588/) (2024)
- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning](https://mlsanity.com/paper/2410.21845/) (2024)
- [Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning](https://mlsanity.com/paper/2405.10292/) (2024)
- [Interactive Post-Training for Vision-Language-Action Models](https://mlsanity.com/paper/2505.17016/) (2025)
- [Improving Vision-Language-Action Model with Online Reinforcement Learning](https://mlsanity.com/paper/2501.16664/) (2025)
- [GRAPE: Generalizing Robot Policy via Preference Alignment](https://mlsanity.com/paper/2411.19309/) (2024)
- [What Can RL Bring to VLA Generalization? An Empirical Study](https://mlsanity.com/paper/2505.19789/) (2025)
- [A Survey on Vision-Language-Action Models: An Action Tokenization Perspective](https://mlsanity.com/paper/2507.01925/) (2025)
- [Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges](https://mlsanity.com/paper/2505.04769/) (2025)
- [RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning](https://mlsanity.com/paper/2412.09858/) (2024)
- [Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation](https://mlsanity.com/paper/2206.11403/) (2022)
- [Offline Reinforcement Learning for Visual Navigation](https://mlsanity.com/paper/2212.08244/) (2022)
- [MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models](https://mlsanity.com/paper/2503.08007/) (2025)
- [Refined Policy Distillation: From VLA Generalists to RL Experts](https://mlsanity.com/paper/2503.05833/) (2025)
- [Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own](https://mlsanity.com/paper/2310.02635/) (2023)
- [SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation](https://mlsanity.com/paper/2410.18065/) (2024)
- [DiffusionRL: Efficient Training of Diffusion Policies for Robotic Grasping Using RL-Adapted Large-Scale Datasets](https://mlsanity.com/paper/2505.18876/) (2025)

## Built on by (most cited first, 5 of 5)

- [A Survey on Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2510.24795/) (2025)
- [Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation](https://mlsanity.com/paper/2605.07381/) (2026)
- [Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories](https://mlsanity.com/paper/2511.19528/) (2025)
- [VINE: Taming Generative Control Policies for Reinforcement Learning](https://mlsanity.com/paper/2607.10369/) (2026)
- [PAKT: Physically-Aligned Kinesthetic Teaching for Reinforcement Learning](https://mlsanity.com/paper/2609.25630/) (2026)

## Abstract (arXiv)

Vision-language-action (VLA) models have shown strong generalization across tasks and embodiments; however, their reliance on large-scale human demonstrations limits their scalability owing to the cost and effort of manual data collection. Reinforcement learning (RL) offers a potential alternative to generate demonstrations autonomously, yet conventional RL algorithms often struggle on long-horizon manipulation tasks with sparse rewards. In this paper, we propose a modified diffusion policy optimization algorithm to generate high-quality and low-variance trajectories, which contributes to a diffusion RL-powered VLA training pipeline. Our algorithm benefits from not only the high expressiveness of diffusion models to explore complex and diverse behaviors but also the implicit regularization of the iterative denoising process to yield smooth and consistent demonstrations. We evaluate our approach on the LIBERO benchmark, which includes 130 long-horizon manipulation tasks, and show that the generated trajectories are smoother and more consistent than both human demonstrations and those from standard Gaussian RL policies. Further, training a VLA model exclusively on the diffusion RL-generated data achieves an average success rate of 81.9%, which outperforms the model trained on human data by +5.3% and that on Gaussian RL-generated data by +12.6%. The results highlight our diffusion RL as an effective alternative for generating abundant, high-quality, and low-variance demonstrations for VLA models.