オンライン強化学習による視覚言語行動モデルの改善
Improving Vision-Language-Action Model with Online Reinforcement Learning
大規模視覚言語行動モデルをオンライン強化学習で改善する際の不安定性と計算負荷に対処するため、強化学習と教師あり学習を交互に繰り返すiRe-VLAフレームワークを提案し、シミュレーションと実機で有効性を検証した。
著者: Yanjiang Guo, Jianke Zhang, Xiaoyu Chen, Xiang Ji, Yen-Jen Wang, Yucheng Hu, Jianyu Chen
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
Recent studies have successfully integrated large vision-language models (VLMs) into low-level robotic control by supervised fine-tuning (SFT) with expert robotic datasets, resulting in what we term vision-language-action (VLA) models. Although the VLA models are powerful, how to improve these large models during interaction with environments remains an open question. In this paper, we explore how to further improve these VLA models via Reinforcement Learning (RL), a commonly used fine-tuning technique for large models. However, we find that directly applying online RL to large VLA models presents significant challenges, including training instability that severely impacts the performance of large models, and computing burdens that exceed the capabilities of most local machines. To address these challenges, we propose iRe-VLA framework, which iterates between Reinforcement Learning and Supervised Learning to effectively improve VLA models, leveraging the exploratory benefits of RL while maintaining the stability of supervised learning. Experiments in two simulated benchmarks and a real-world manipulation suite validate the effectiveness of our method.
