ALL INTELLIGENCE
OpenAI 官方博客T1·Agents

OpenAI Robot Hand Solves Rubik's Cube via Sim-to-Real RL

Original title: Solving Rubik’s Cube with a robot hand
78AI Score

OpenAI trained neural networks entirely in simulation using Automatic Domain Randomization (ADR) to enable a human-like robot hand to solve the Rubik's Cube. This breakthrough demonstrates that reinforcement learning can achieve unprecedented dexterity and zero-shot transfer from virtual to physical environments.

Full Report

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.