GRASP authors compare with SuperMimic: extracting more optimization signal from sim experience
hankyang94 · x · 2026-11-01
The GRASP authors add a methodological comparison: recent SuperMimic trains tracking policies by backpropagating through a learned world model, while GRASP recovers trajectory-cost gradients from local models fitted to archived simulator rollouts, refining motion references before downstream policy learning. Both point to an exciting opportunity — extracting more useful optimization information from simulation experience. Paper, code, and demos are available.
More from Embodied
- Naval predicts 4-passenger drones will eventually end commercial air travel, with a long interregnum ahead — naval · 2026-11-01
- Meta Quest game scans your real room and turns it into a haunted house — Scobleizer · 2026-11-01
- RoboAuto: Robot Program Search With Multi-Level Physical Understanding — DJiafei · 2026-11-01
- Developer dresses robot 'Bob' as a ghost to hand out Halloween candy — chrismatthieu · 2026-11-01
- Harvard's GRASP refines human demos in physics sim for dexterous hands and Unitree G1 — hankyang94 · 2026-11-01
- Neuralink user designs 3D-printed parts with thoughts alone, holds them hours later — Scobleizer · 2026-11-01