Siemens and Berkeley introduce ARLI for RL fine-tuning of VLAs under inference latency
svlevine · x · 2026-09-22
ARLI (Asynchronous RL with Intermediate Information) from Siemens, UC Berkeley and collaborators tackles why async VLA inference breaks the Markov assumption needed for RL fine-tuning. A small, faster RL policy observes more recent images and steers a large robot foundation model, using state augmentations (committed actions + mid-inference observation) to restore near-Markovian structure. Experiments show ARLI enables effective finetuning under latency where standard RL fails entirely, even matching no-latency RL performance.
More from Embodied
- NUS's Grounded Action Model Tops Robot Manipulation Benchmarks with 3D Grounding — NationalUniversityofSingapore · 2026-09-22
- Distilling World-Model Features into VLAs: 0.8B Policy Hits 97.9% on LIBERO — Trung Dao · 2026-09-22
- HIRO Industries Unveils Origin: A 17-DOF Dual-Arm Robot for Packing and Kitting Workstations — Scobleizer · 2026-09-22
- Stealth team unveils new robot Origin; Scobleizer bets it would sell at Home Depot — Scobleizer · 2026-09-22
- Figure's Helix 2.5 robots tested on household tasks across 30 unseen homes — FinanceYF5 · 2026-09-22
- PrimeBOT T1 starts at $2,960 as line outputs a humanoid every 2.5 minutes — davidpattersonx · 2026-09-22