Article

π-StepNFT: A Step-wise Negative-aware Online Reinforcement Learning Framework for Streaming VLAs

The authors propose π-StepNFT, an online reinforcement learning framework for streaming VLAs that treats transitions in SDE sampling as supervision units and uses variance-normalized transition errors to distinguish positive and negative velocity branches, without computing the final-action likelihood.

Part of the event: Authors propose π-StepNFT online reinforcement learning framework for streaming VLA

This page provides a summary and source link only.