OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models
arXiv:2610.12914v1 Announce Type: new Abstract: Vision-language-action (VLA) models have shown strong promise in robotic manipulation, yet their post-training still predominantly relies on trajectory-level supervised imitation over robot demonstrations. While effective for learning feasible actions…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-10-12 04:00 · arXiv cs.AI
OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models