Play2Perfect (CoRL 2026): Play Pretraining Yields Precise Zero-Shot Robot Assembly
leto__jean · x · 2026-09-11
Stanford's Play2Perfect, accepted to CoRL 2026, uses a 2-stage RL pipeline: free-space "play" pretraining to build manipulation priors, then sparse-reward finetuning on contact-rich precise assembly (screwing, tight insertion, real-size plug/fork), with zero-shot sim-to-sim transfer from Isaac Sim to MuJoCo. Systematic ablations show pretraining transfers best when robots manipulate objects in-hand with fingers; from-scratch training with hand-crafted dense rewards stalls near zero. The team also generated 2 new envs from scratch with Opus 5, reusing the same RL code. An interactive browser demo is live.
Related event: Stanford's Play2Perfect accepted to CoRL 2026 with zero-shot assembly(2 posts)→
More from Embodied
- Figure's Brett Adcock teases 'max AGI' humanoid, robots roam HQ autonomously — adcock_brett · 2026-09-11
- Tesla FSD spots oncoming cars through sun glare, credits photon count reconstruction — yunta_tsai · 2026-09-11
- NVIDIA says every major robotaxi program runs on its stack, market seen at $400B by 2035 — nordicinst · 2026-09-11
- Robotics startup Skild AI hits $100M ARR just 10 months after first deployment — deepakpathak · 2026-09-11
- McKinsey report calls humanoid robots a media distraction, sees just 2% of Physical AI market by 2045 — kscottz · 2026-09-11
- Simulated zebrafish and vision-equipped robot fish reveal how the body shapes brain circuits — DoctorJosh · 2026-09-11