Training pi0.5 on OpenArm: from teleop data to a 100% pick-and-place policy
Fine-tuning SmolVLA for Cube Pick-and-Place on SO-101
HIL-SERL for SO-101: Real-World Grasping from Scratch
Teaching a Robot to Grasp from Pixels in MuJoCo
Training an SO-101 RL Agent to Grasp and Lift in MuJoCo