OpenAI 训练了一对神经网络，用一只仿人机械手解开魔方。这对网络完全在仿真中训练，用的是与 OpenAI Five 相同的强化学习代码，并搭配一种叫自动域随机化（Automatic Domain Randomization, ADR）的新技术。该系统能应对训练时从未见过的情况，比如被一只毛绒长颈鹿戳动。这说明强化学习不只是处理虚拟任务的工具，也能解决需要前所未有灵巧度的物理世界问题

正文

We’ve trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand. The neural networks are trained entirely in simulation, using the same reinforcement learning code as OpenAI Five paired with a new technique called Automatic Domain Randomization (ADR). The system can handle situations it never saw during training, such as being prodded by a stuffed giraffe. This shows that reinforcement learning isn’t just a tool for virtual tasks, but can solve physical-world problems requiring unprecedented dexterity.