paper-with-me

홈 › Papers

RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models

2025-10-08 · Hongzhi Zang, Mingjie Wei, Si Xu, Yongji Wu, Zhen Guo, Yuanqing Wang, Hao Lin, Peihong Wang, Liangzhi Shi, Yuqing Xie, Zhexuan Xu, Zhihao Liu, Kang Chen, Wenhao Tang, Quanlu Zhang, Weinan Zhang, Chao Yu, Yu Wang arxiv

Recent advances in vision-language-action (VLA) models have motivated the extension of their capabilities to embodied settings, where reinforcement learning (RL) offers a principled way to optimize task success through interaction. However, existing methods remain fragmented, lacking both a unified platform for fair comparison across architectures and algorithms and an efficient system design for scalable training. To address these challenges, we introduce RLinf-VLA, a unified and efficient framework for scalable RL training of VLA models. RLinf-VLA achieves unification by providing a unified interface that standardizes the integration of diverse VLA architectures, multiple RL algorithms, and heterogeneous simulators, enabling extensibility. To ensure efficiency, the system adopts a flexible resource allocation architecture for rendering, inference, and training workloads in RL pipelines. In particular, for GPU-parallelized simulators, RLinf-VLA introduces a hybrid fine-grained pipeline allocation strategy, yielding a 1.61x-1.88x training speedup. Using this unified system, models trained with RLinf-VLA demonstrate consistent performance improvements of approximately 20-85% across multiple simulation benchmarks, including LIBERO, ManiSkill, and RoboTwin. Furthermore, we distill a set of training practices for effective RL-based VLA training. We position RLinf-VLA as a foundational system to enable efficient, unified, and reproducible research in embodied intelligence.

📄 PDF Abstract BibTeX arXiv:2510.06710

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation

2025-09-19 · Chao Yu, Yuanqing Wang, Zhen Guo, Hao Lin 외 arxiv

Reinforcement learning (RL) has demonstrated immense potential in advancing artificial general intelligence, agentic intelligence, and embodied intelligence. However, the inherent heterogeneity and dynamicity of RL workf…

Reinforcement Learning

RLinf-USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI

2026-02-08 · Hongzhi Zang, Shu'ang Yu, Hao Lin, Tianxing Zhou 외 arxiv

Online policy learning directly in the physical world is a promising yet challenging direction for embodied intelligence. Unlike simulation, real-world systems cannot be arbitrarily accelerated, cheaply reset, or massive…

Reinforcement Learning

Unified Reinforcement and Imitation Learning for Vision-Language Models

2025-10-22 · Byung-Kwan Lee, Ryo Hachiuma, Yong Man Ro, Yu-Chiang Frank Wang 외 arxiv

Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learn…

Reinforcement LearningText Generation

VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning

2025-05-17 · Yuqi Liu, Tianyuan Qu, Zhisheng Zhong, Bohao Peng 외

Large vision-language models exhibit inherent capabilities to handle diverse visual perception tasks. In this paper, we introduce VisionReasoner, a unified framework capable of reasoning and solving multiple visual perce…

2D Object DetectionObject CountingReasoning SegmentationReferring Expression Segmentation+4

Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models

2025-05-23 · Xuchen Pan, Yanxi Chen, Yushuo Chen, Yuchang Sun 외

Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models. It is built with a decoupled design, consisting of (1) an RFT-core that unifies and…