Reshaping Action Error Distributions for Reliable Vision-Language-Action Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914305029439488 |
|---|---|
| author | Bai, Shuanghao Wang, Dakai Chi, Cheng Zhou, Wanqi Lyu, Jing Zhao, Xiaoguang Wang, Pengwei Wang, Zhongyuan Xing, Lei Zhang, Shanghang Chen, Badong |
| author_facet | Bai, Shuanghao Wang, Dakai Chi, Cheng Zhou, Wanqi Lyu, Jing Zhao, Xiaoguang Wang, Pengwei Wang, Zhongyuan Xing, Lei Zhang, Shanghang Chen, Badong |
| contents | In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies. Most existing VLA frameworks rely on standard supervised objectives, typically cross-entropy for discrete actions and mean squared error (MSE) for continuous action regression, which impose strong pointwise constraints on individual predictions. In this work, we focus on continuous-action VLA models and move beyond conventional MSE-based regression by reshaping action error distributions during training. Drawing on information-theoretic principles, we introduce Minimum Error Entropy (MEE) into modern VLA architectures and propose a trajectory-level MEE objective, together with two weighted variants, combined with MSE for continuous-action VLA training. We evaluate our approaches across standard, few-shot, and noisy settings on multiple representative VLA architectures, using simulation benchmarks such as LIBERO and SimplerEnv as well as real-world robotic manipulation tasks. Experimental results demonstrate consistent improvements in success rates and robustness across these settings. Under imbalanced data regimes, the gains persist within a well-characterized operating range, while incurring negligible additional training cost and no impact on inference efficiency. We further provide theoretical analyses that explain why MEE-based supervision is effective and characterize its practical range. Project Page: https://cognition2actionlab.github.io/VLA-TMEE.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04228 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Reshaping Action Error Distributions for Reliable Vision-Language-Action Models Bai, Shuanghao Wang, Dakai Chi, Cheng Zhou, Wanqi Lyu, Jing Zhao, Xiaoguang Wang, Pengwei Wang, Zhongyuan Xing, Lei Zhang, Shanghang Chen, Badong Robotics In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies. Most existing VLA frameworks rely on standard supervised objectives, typically cross-entropy for discrete actions and mean squared error (MSE) for continuous action regression, which impose strong pointwise constraints on individual predictions. In this work, we focus on continuous-action VLA models and move beyond conventional MSE-based regression by reshaping action error distributions during training. Drawing on information-theoretic principles, we introduce Minimum Error Entropy (MEE) into modern VLA architectures and propose a trajectory-level MEE objective, together with two weighted variants, combined with MSE for continuous-action VLA training. We evaluate our approaches across standard, few-shot, and noisy settings on multiple representative VLA architectures, using simulation benchmarks such as LIBERO and SimplerEnv as well as real-world robotic manipulation tasks. Experimental results demonstrate consistent improvements in success rates and robustness across these settings. Under imbalanced data regimes, the gains persist within a well-characterized operating range, while incurring negligible additional training cost and no impact on inference efficiency. We further provide theoretical analyses that explain why MEE-based supervision is effective and characterize its practical range. Project Page: https://cognition2actionlab.github.io/VLA-TMEE.github.io/ |
| title | Reshaping Action Error Distributions for Reliable Vision-Language-Action Models |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.04228 |