AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Stable and Efficient Real-World Online VLA Post-Training via Asynchronous Replay-Anchored Policy Improvement

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

Online post-training of vision-language-action (VLA) models requires efficient use of robot interaction and reliable policy improvement from continually collected experience. We propose asynchronous Replay-Anchored Policy improvement (RAPolicy), a framework that performs rollout and learning concurrently while grounding both critic and actor updates in replayed behavior. The critic learns chunk-level values from recorded actions and constructs Bellman targets without predicting next actions, reducing computation and dependence on action-value estimates outside replay coverage. The one-step flo

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-23T12:01:45.602Z. This is not the publication date.