4 papers · 1 filter
WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
Zhennan Jiang, Shangqing Zhou, Yutong Jiang +11
Reinforcement learning (RL) promises to unlock capabilities beyond imitation learning for Vision--Language--Action (VLA) models, but its requirement for massive real-world interact…
Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning
Dongjie Yu, Kun Lei, Zhennan Jiang +2
Pretrained imitation policies have become a strong foundation for robot manipulation, but they often require online improvement to overcome execution errors, limited dataset covera…
Posterior Optimization with Clipped Objective for Bridging Efficiency and Stability in Generative Policy Learning
Yuhui Chen, Haoran Li, Zhennan Jiang +4
Expressive generative models have advanced robotic manipulation by capturing complex, multi-modal action distributions over temporally extended trajectories. However, fine-tuning t…
RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning
Kun Lei, Huanyu Li, Dongjie Yu +6
Real-world robotic manipulation in homes and factories demands reliability, efficiency, and robustness that approach or surpass those of skilled human operators. We present RL-100,…