StructRL: 長期的視覚-言語-行動タスクのためのオンライン構造化強化学習
StructRL: Online Structured Reinforcement Learning for Long-Horizon Vision-Language-Action Tasks
長期的なロボット操作タスクを検証可能なサブタスクに分解し、前提条件が満たされた段階で中間報酬を与えるオンライン強化学習フレームワークを提案。VLAモデルのポストトレーニング性能を向上させる。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Ziyi Yin, Sangmin Woo, Kang Zhou, Sungyeon Kim, Aosong Feng, Haibo Ding, Jun Huan
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
Vision-language-action (VLA) models perform well on shorter-horizon manipulation tasks but still struggle with long-horizon tasks that require multiple dependent manipulations from a single command. Online reinforcement learning (RL) can improve these policies through environment interaction, yet many existing methods provide reward only after the complete task succeeds. However, such terminal supervision is sparse and does not distinguish early failures from rollouts that make substantial partial progress. We propose StructRL, an online RL framework that constructs structured intermediate supervision from verifiable subtask completions. StructRL decomposes each task into verifiable subtasks, grants intermediate rewards only after the prerequisite subtasks have been completed, and scales each reward according to completion pace. Across RoboCasa365 and LIBERO-Long with GR00T-N1.5 and pi 0.5, StructRL consistently outperforms evaluated online RL baselines. These results show that verifiable, structured intermediate rewards improve long-horizon VLA post-training. Code is available at https://github.com/amazon-science/StructRL.