RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning

ArXi:2510.14830v4 Announce Type: replace-cross 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, a real-world reinforcement learning framework built on diffusion visuomotor policies. RL-100 unifies imitation and reinforcement learning under a single clipped PPO surrogate objective applied within the denoising process, yielding conservative and stable improvements across offline and online stages.