Berkeley project uses pretrained base policy's support to guide exploration for fast online adaptation
abhishekunique7 · x · 2026-11-05
JacobBerg33 shares his first project at UC Berkeley: an algorithm for fast online adaptation that uses the support of a pretrained base policy to guide exploration, while letting the actor improve beyond it. A detailed technical thread is promised to follow.
More from Embodied
- Corebrum OS adds built-in VNC screen share, demoed remote-viewing an NVIDIA Thor robot from a Mac — chrismatthieu · 2026-11-05
- NerF Author Ben Mildenhall Teases Mystery AI Gadget With Robot Icon and 8:00 Display — XRarchitect · 2026-11-05
- KAIST's H2RB transfers human demonstrations to robots, boosting object transfer from 8.0 to 51.8 — kaist-ai · 2026-11-05
- New AI glasses UI concept demo shows off futuristic interface design — AnhPhuNguyen1 · 2026-11-05
- "Robotics simulation platform" startups are a dead end — agents already removed the need — carlosdponx · 2026-11-05
- Runtime (YC F26) debuts simulation-to-real robot policies, threads a rope with no fine-tuning — ycombinator · 2026-11-05