Berkeley's QF3: off-policy flow RL with filtered Q-gradients trains humanoids from scratch
berkeley_ai · x · 2026-10-15
UC Berkeley researchers (led by ChungMinKim) introduce QF3: Fast Flow RL with Filtered Q-Gradients, an off-policy addition to their flow-policy RL series. The recipe: hill-climb on ∇Q, filter for stability, and flow-match the replay buffer. It is sample-efficient and works on humanoids from scratch, VLA fine-tuning, and even image models.
Related event: Berkeley Releases QF3: Filtered Q-Gradients for Flow-Based Robot RL(3 posts)→
More from Embodied
- Atlanta apartment complex deploys robot security dogs that patrol at night and talk to residents — 4KTV · 2026-10-15
- dm_robots co-founder lands in Hong Kong to build China network, starting two-week GBA tour — DominiqueCAPaul · 2026-10-15
- Rhoda's tactile-sensor robot retrieves objects blindfolded, sensing texture and heat — DhruvBatra_ · 2026-10-15
- Valeo and KE:SAI launch open-source initiative for generalist autonomous driving AI — abursuc · 2026-10-15
- ASENA: A Coding Agent Writes and Fixes Programs On-the-Fly to Drive a G1 Humanoid — Lianhuiq · 2026-10-15
- Bittensor SN44 bets on generative world models as a simulation engine for robotics — richdotca · 2026-10-15