Jul 2026
VINE: Taming Generative Control Policies for Reinforcement Learning
VINE is proposed, an RL-oriented sampling method that enables stable end-to-end value-gradient optimization for flow-matching policies and achieves stable policy improvement and consistently outperforms state-of-the-art RL methods on the OGBench offline RL benchmark and real-world robotic manipulation task.
Rushuai Yang, Zhuo Han, Houlin Li et al.
· arXiv.org · 0 citations