OpenAI 机器人手解魔方:Sim-to-Real 新突破

原标题:Solving Rubik’s Cube with a robot hand
78AI 研判分

OpenAI 利用自动域随机化(ADR)技术,在纯模拟环境中训练神经网络,使仿人机械手成功解决魔方难题。该成果证明了强化学习结合 ADR 能实现从虚拟到物理世界的零样本迁移,展示了前所未有的操作灵巧性。

报道正文

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.