Spiced self-play accepted at CoRL: just 30 minutes of human data biases agents to right conventions
EugeneVinitsky · x · 2026-09-10
The spiced self-play paper has been accepted to CoRL. Eugene Vinitsky's takeaway: when skills can be learned from self-play, human data still matters — but only a little. Just 30 minutes of human demonstrations is enough to bias agents toward picking up the right conventions instead of converging on alien solutions.
More from Embodied
- CoRL paper: flow-matching VLAs can run 1-step Euler inference with no retraining — kaixhin · 2026-10-26
- Robotic dexterity should be judged on speed, force control and tool use, not copying humans — DJiafei · 2026-10-26
- Shenzhen company combines humanoid robots with industrial robot arms — RoboBalaji · 2026-10-26
- Realbotix, a sex-doll maker, unveils Echo humanoid with lifelike face — CyberRobooo · 2026-10-26
- Track bolt robot tightens railway fasteners in 6–7 seconds with sub-mm precision — RoboBalaji · 2026-10-26
- Tesla FSD (Supervised) Approved in Latvia, Its 10th European Country — XFreeze · 2026-10-26