arXiv Machine Learning By Tongyan Fang, Siyuan Huang, Naiyu Fang, Ganlong Zhao, Zhongjin Luo, Jianbo Liu, Xiaogang Wang, Ying Dong, Hongsheng Li

Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes

Read the original on arXiv Machine Learning →

arXiv:2606. 17043v1 Announce Type: cross Abstract: When pretrained VLA policies are fine-tuned through online RL, each rollout episode produces only a single binary outcome (success or failure), yet the actor update requires per-transition supervision.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.