mit-han-lab/pear
Training Reasoning Models in Simulation to Natively Use Real Robots
- Stars292
- LanguagePython
- LicenseApache-2.0
Training Reasoning Models in Simulation to Natively Use Real Robots
Training Reasoning Models in Simulation to Natively Use Real Robots
PEAR is a post-training engine for agentic robotics: it trains reasoning models to natively use robots, with reinforcement learning in simulation.
PEAR is the training infrastructure behind Training Reasoning Models in Simulation to Natively Use Real Robots, where an open 27B reasoning model learns to use real robots entirely in simulation, with zero demonstrations.
Description and README excerpt from mit-han-lab/pear on GitHub ↗.
mit-han-lab/pear was first seen on GitHub · Rising today on Nov 15, 2026. Since then it has appeared in 34 checks on 2 different days. Its best position was #9 of 30, reached on Nov 15, 23:46 UTC. It is #11 right now, holding steady at #11 over the last 6 checks.
Position on GitHub · Rising today at every check (lower is better).
Best rank per day (UTC).
stars as reported by GitHub.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 16, 06:01 UTC it is #11, holding steady at #11 over the last 6 checks.
#9 on GitHub · Rising today, on Nov 15, 23:46 UTC. Trendoday checks this list every 60 minutes.
It was first seen on Nov 15, 2026 and has been on the list on 2 days (34 checks) since.
Mostly Python; it is licensed under Apache-2.0. It has 292 stars and 21 forks.