VLRLA: Deployment-Time Adaptation of Vision-Language-Action Models through In-Context Reinforcement Learning
From the 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.
From the abstract. Our summary is in progress.
The full text is not republished here because the paper's license does not allow it. Read the original on arXiv.