Learning dexterous in-hand manipulation
We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies that can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The t...
Publications
2 shownCascaded pose regression
We present a fast and accurate algorithm for computing the 2D pose of objects in images called cascaded pose regression (CPR). CPR progressively refines a loosely specified init...
Frequent Co-Authors
Researcher Info
- h-index
- 2
- Publications
- 2
- Citations
- 2,050
- Institution
- OpenAI (United States)
External Links
Impact Metrics
h-index
2
h-index: Number of publications with at least h citations each.