Locomotion policy trained in under 30 seconds with zero-order policy gradient
breadli428 · x · 2026-10-26
A demo of training a locomotion policy in under half a minute using zero-order policy gradient. The author argues the speedup from first-order gradients with BPTT over zero-order PG is minor, and even more ignorable with a learned world model where samples are incredibly cheap.
Related event: Debate over world-model gradients: zero-order wins on speed(2 posts)→
More from Embodied
- Chums: open-source Apple Watch app puts Claude Code and Codex on your wrist — brandon_galang · 2026-10-27
- Dev uses Grok bot to turn ESP into an iPhone accessory for syncing robot servos — Baconbrix · 2026-10-27
- NVIDIA releases MotionBricks: real-time humanoid motion generation at 15,000 FPS with 2ms latency — _akhaliq · 2026-10-26
- Claude Code finds root backdoor in Honda Civic head unit, then debloats it — IndraVahan · 2026-10-26
- Temple health wearable opens pre-orders, users ask: why wear it before benefits are proven — abhishekcode42 · 2026-10-26
- FLASH: GPU-native deformable sim learns cloth folding in minutes on one RTX 5090 — ChongZzZhang · 2026-10-26