外观
论文arXiv 2610.1951714 天前
VLRLA：通过 In-Context Reinforcement Learning 实现 Vision-Language-Action 模型的部署时适应
原文链接：VLRLA: Deployment-Time Adaptation of Vision-Language-Action Models through In-Context Reinforcement Learning（arXiv 2610.19517 · 发布日期：2026-10-14）
VLRLA: Deployment-Time Adaptation of Vision-Language-Action Models through In-Context Reinforcement Learning
提出VLRLA框架，为VLA模型加入上下文强化学习，在仿真和真实部署中验证部署时适应能力。
核心要点
- 预训练VLA策略缺乏在部署中利用累积交互经验逐步适应的机制。
- VLRLA为现有VLA模型增设强化学习模块，利用历史观测、动作、奖励和终止信号学习。
- 部署期间保持模型参数固定，策略逐步细化动作生成并提升任务成功率。
- 实验系统研究了VLRLA在仿真中的学习性质，并展示其在真实未见场景中的适应能力。
验证范围与局限：验证范围包括仿真实验和真实部署中的未见场景，摘要未说明具体任务或机器人数量。
英文摘要 (Abstract)
Vision-language-action (VLA) models connect visual perception and language understanding with robot control, providing a foundation for instruction-conditioned manipulation. However, conventional pretrained VLA policies lack a mechanism for gradual adaptation through accumulated interaction experience during deployment. We therefore propose VLRLA, a general framework that equips existing VLA models with \textit{in-context reinforcement learning} capabilities for deployment-time adaptation. Our approach augments a VLA model with a reinforcement learning module that learns from historical observations, actions, rewards, and termination signals. During deployment, the policy gradually refines its action generation and progressively improves task success while keeping model parameters fixed. Our approach is also designed for general applicability and compatibility with diverse learning history construction strategies and model training pipelines. Finally, through extensive experiments, we systematically investigate the learning properties of VLRLA in simulation and demonstrate its ability to adapt to unseen scenarios during real-world deployment.
作者：Diyuan Shi, Yiqi Tang, Hongyin Zhang, You Wu, Donglin Wang
来源
本页事实对应的公开页面，以原文为准。