Training a robot locomotion policy inside a world model on an RTX 4070 Super
victormustar · x · 2026-10-31
Developer Matthias Caro shares a hands-on experiment: SuperMimic-style training of an FPM + locomotion policy entirely inside a world model on an RTX 4070 Super. Results are far from perfect — the force assistance curriculum didn't carry over — but sparse terrain success was a surprise. The author finds the direction very promising, though unsure about deploying such a policy in the real world.
More from Embodied
- VITURE launches $599 Phantom Beast XR glasses in Phantom Blade Zero collab — Scobleizer · 2026-10-31
- Agility Robotics lost $138.1M in 2025 as Brett Adcock's doom prediction nears — Rewkang · 2026-10-31
- Promised the Year of Physical AI: Humanoid Robots Are Behind Schedule — Distinct-Question-16 · 2026-10-31
- PokeBot's RoboAPI brings the call-a-model pattern to robot arms, no task training needed — rohanpaul_ai · 2026-10-31
- Foundry Robotics raises $100M Series A to build factories that look like data centers — ishabytes · 2026-10-31
- NVIDIA's MotionBricks robotics motion-generation model trends on Hugging Face — nvidia · 2026-10-31