Outcome-Balanced PPO 与策略诱导流整流:面向 Flow VLA 策略的强化学习框架
Outcome-Balanced PPO and Policy-Induced Flow Rectification for Flow-Based VLA Policies
AI 导读
arXiv 论文提出一个结合 Outcome-Balanced PPO 与策略诱导流整流的强化学习框架,用于对 flow-based 视觉-语言-动作(VLA)策略做后训练。
正文 · 原文
Abstract:Reinforcement learning (RL) enables post-training of flow-based vision-language-action (VLA) policies by optimizing expected task return through environment interaction. However, this optimization raises two challenges: policy updates can alter the velocity-field geometry underlying the score approximation used for stochastic transitions, and sparse multi-task rollouts can yield uneven learning signals across tasks and advantage signs. We introduce an RL framework that combines Outcome-Balanced Proximal Policy Optimization (PPO) with policy-induced flow rectification. Outcome-Balanced PPO reweights positive advantages using task success-rate estimates and rescales positive and negative advantages while preserving their signs. Policy-induced rectification periodically fits a linear-bridge flow to ODE endpoint pairs generated by the current policy, refreshing the representation used in subsequent stochastic optimization. We evaluate the framework on simulated manipulation benchmarks and additionally study a component combination in a Real2Sim2Real task, examining task performance, optimization behavior, and flow consistency. The proposed framework improves success rates over the evaluated baselines across the simulated benchmarks.
| Comments: | 15 pages |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.22878 [cs.AI] |
| (or arXiv:2611.22878v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22878 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuhan Wang [view email]
[v1]
Tue, 17 Nov 2026 14:52:57 UTC (820 KB)
来源:arXiv cs.AI · arxiv.org