dexterous in-hand manipulation with learned world modelsIntermediate
Dexterity from Supervised Play
In this preprint, Amazon's frontier robotics lab shows that fifteen minutes of a person aimlessly 'playing' with a cube through a data glove can teach a multi-fingered robot hand to keep collecting its own training data, and then to turn the cube to any requested orientation. In simulation the method reached the goal within 0.6 rad in 91.4% of trials, while a standard reinforcement-learning baseline needed roughly 490 times more interaction to match it.