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 mismatches the unique characteristics of VLA training, as physical simulators introduce highly variable, resource-intensive latencies. To address this, we introduce RL-VLA$^3$, a fully asynchronous distributed RL framework that enables fine-grained asynchronous interaction between simulation, inference, and training components through dynamic batching schedulers and flexible environment sharding strategies. Extensive experiments across diverse simulation backends, VLA architectures, and RL algorithms demonstrate that RL-VLA$^3$ achieves throughput improvements of up to 85.2\% over synchronous baselines while maintaining identical sample efficiency, with scalability validated from 8 to 256 GPUs. To our knowledge, RL-VLA$^3$ is the first fully asynchronous RL training framework tailored specifically for the system-level challenges of VLA training.
AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models
KU Leuven, Dept. Mechanical Engineering, Research unit Robotics, Automation and Mechatronics(库勒恩大学,机械工程系,机器人、自动化与机电一体化研究单位);KU Leuven, Dept. Electrical Engineering, Research unit Processing Speech and Images(库勒恩大学,电气工程系,语音和图像处理研究单位)
VacuumVLA: Boosting VLA Capabilities via a Unified Suction and Gripping Tool for Complex Robotic Manipulation
The Chinese University of Hong Kong(香港中文大学);Shanghai Jiao Tong University(上海交通大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);DiDi Global(滴滴出行)
Harmonizing Real-Time Constraints and Long-Horizon Reasoning: An Asynchronous Agentic Framework for Dynamic Scheduling
School of Computer Science and Engineering, Beihang University, Beijing 100191, China(北京航空航天大学计算机科学与工程学院);Shenzhen Loop Area Institute, Shenzhen, China(深圳环形区研究所);Qingdao Research Institute, Beihang University(青岛研究院);Hangzhou Innovation Institute, Beihang University(杭州创新研究院);School of Artificial Intelligence, Xidian University, Xi’an 710071, Shaanxi, China(西安电子科技大学人工智能学院);Guangzhou Institute of Technology, Xidian University, Guangzhou 510555, Guangdong, China(广州技术研究所)
Deep Reinforcement Learning Microgrid Optimization Strategy Considering Priority Flexible Demand Side
Changchun Institute of Technology(长春工程学院);National and Local Joint Engineering Research Center for Smart Distribution Network Measurement, Control and Safe Operation Technology(智能配电网测控与安全运行技术国家地方联合工程研究中心);Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学(山东省科学院));Institute of Oceanographic Instrumentation(海洋仪器研究所)