Quadruped RL training in 1 minute on an M1 MacBook via mjbatch with 1024 parallel envs
philfung · x · 2026-09-12
kevinzakka open-sourced mjbatch (317 GitHub stars): MuJoCo batched parallel simulation training a Go1 quadruped to follow joystick commands across 1024 parallel environments, solving the task in just 1 minute on a 5-year-old M1 MacBook. The repo includes the full 400-line go1joystick.py training script, showing consumer laptops can handle large-scale parallel robot RL.
More from Embodied
- cixliv: robot fighting may be the first realized market where bots beat average humans — cixliv · 2026-10-28
- Can the Hiwonder MentorPi T1 run fully offline as a robot pet? Pi 5 questioned — oulu2006 · 2026-10-28
- Testing Mint Modeler to Build the Menlo Research Robot — freelerobot · 2026-10-28
- Khosla-backed startup builds a 'mind-reading' cap with 100,000 tiny chips to write AI prompts — Distinct-Question-16 · 2026-10-28
- Racer turns Ray-Ban Meta glasses into an AI track coach with Opus 5.5, gains 5.3 seconds per lap — Vjeux · 2026-10-28
- Fine-tuning VLAs on TAMP data hits distribution mismatch; DATAFARM gets JAX port — tomssilver · 2026-10-28