OpenAI Blog company blog
Solving the Rubik’s cube with a robot hand
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…
- Points
- 171
- HN comments
- 46
- Submissions
- 1
- Cited by
- 6 commenters
AI & Machine LearningHardware & Electronics2019
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Oct 15, 2019 | Solving the Rubik’s cube with a robot hand by gdb | 171 | 46 |
Cited in comments
Linked from 6 Hacker News comments by 6 different people, from Oct 2019 to Aug 2022.
Most recent:
- lambdatronics · Aug 20, 2022
- edouard-harris · May 12, 2022
- diplodocusaur · Sep 23, 2021
- w_t_payne · Jul 2, 2020
- skolman · May 6, 2020
- Voloskaya · Oct 31, 2019
