RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training

arXiv:2602.05765v2 Announce Type: replace Abstract: Reinforcement learning (RL) has emerged as a critical paradigm for post-training Vision-Language-Action (VLA) models, enabling embodied agents to adapt and improve through environmental interaction. However, existing RL frameworks for VLAs inherit synchronous design principles from traditional LLM training, treating entire rollouts as indivisible units and alternating strictly between data collection and policy optimization. This fundamentally