🚨 Stop feeding your world model the same boring demos. Switch to free-range play data! 🚨
Our CoRL 2026 paper finds we can optimize autonomous data collection to focus on missing action consequences, achieving up to 85x the data scaling efficiency of expert data collection!🧵
@Vaibhavdixit02 Another take from research perspective: if you can get it to work on a humanoid, you can probably make it work on most existing robots. If a humanoid can manipulate then so can a fixed base manipulator or a wheeled robot but the other way might not be true always.
@pr0t0_01 Would love to know what are the improvements that make your robots faster and more expressive than openduck mini or Disney while still looking similar
Can robots learn to jump, crawl, and climb—without reward engineering, curriculum learning, or reference data?
In our #CoRL2025 paper SDAX, Skill Discovery as eXploration, we show how unsupervised RL can learn these challenging motor skills without human priors —and transfer them to real robots.
📷 Unsupervised Skill Discovery as Exploration for Learning Agile Locomotion
Seungeun Rho* @ross_rho , Kartik Garg* @_pacificax, Morgan Byrd, Sehoon Ha @sehoonha
https://t.co/Hy4lpDX75r