paper-with-me

홈 › Papers

VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators

2025-10-01 · Hengtao Li, Pengxiang Ding, Runze Suo, Yihao Wang, Zirui Ge, Dongyuan Zang, Kexian Yu, Mingyang Sun, Hongyin Zhang, Donglin Wang, Weihua Su arxiv

Vision-Language-Action (VLA) models enable embodied decision-making but rely heavily on imitation learning, leading to compounding errors and poor robustness under distribution shift. Reinforcement learning (RL) can mitigate these issues yet typically demands costly real-world interactions or suffers from sim-to-real gaps. We introduce VLA-RFT, a reinforcement fine-tuning framework that leverages a data-driven world model as a controllable simulator. Trained from real interaction data, the simulator predicts future visual observations conditioned on actions, allowing policy rollouts with dense, trajectory-level rewards derived from goal-achieving references. This design delivers an efficient and action-aligned learning signal, drastically lowering sample requirements. With fewer than 400 fine-tuning steps, VLA-RFT surpasses strong supervised baselines and achieves greater efficiency than simulator-based RL. Moreover, it exhibits strong robustness under perturbed conditions, sustaining stable task execution. Our results establish world-model-based RFT as a practical post-training paradigm to enhance the generalization and robustness of VLA models. For more details, please refer to https://vla-rft.github.io/.

📄 PDF Abstract BibTeX arXiv:2510.00406

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning

2025-08-04 · Dongchi Huang, Zhirui Fang, Tianle Zhang, Yihang Li 외 arxiv

Vision-Language-Action (VLA) models demonstrate significant potential for developing generalized policies in real-world robotic control. This progress inspires researchers to explore fine-tuning these models with Reinfor…

Reinforcement LearningOffline RL

STARE-VLA: Progressive Stage-Aware Reinforcement for Fine-Tuning Vision-Language-Action Models

2025-12-04 · Feng Xu, Guangyao Zhai, Xin Kong, Tingzhong Fu 외 arxiv

Recent advances in Vision-Language-Action (VLA) models, powered by large language models and reinforcement learning-based fine-tuning, have shown remarkable progress in robotic manipulation. Existing methods often treat …

Reinforcement Learning

VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning

2025-06-20 · Zhangyang Qi, Zhixiong Zhang, Yizhou Yu, Jiaqi Wang 외

Vision-Language Navigation (VLN) is a core challenge in embodied AI, requiring agents to navigate real-world environments using natural language instructions. Current language model-based navigation systems operate on di…

NavigateVision-Language Navigation

Improving Vision-Language-Action Model with Online Reinforcement Learning

2025-01-28 · Yanjiang Guo, Jianke Zhang, Xiaoyu Chen, Xiang Ji 외

Recent studies have successfully integrated large vision-language models (VLMs) into low-level robotic control by supervised fine-tuning (SFT) with expert robotic datasets, resulting in what we term vision-language-actio…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Vision-Language-Action

EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models

2026-05-25 · Perry Dong, Kuo-Han Hung, Tian Gao, Dorsa Sadigh 외 arxiv

The ability to efficiently and reliably learn new tasks has been a foundational challenge in robotics. Vision-Language-Action (VLA) models have demonstrated strong generalization across diverse manipulation tasks, yet pr…

Reinforcement Learning