模倣を超えて：VLAモデルのための強化学習ベースのSim-Real協調学習
Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models
実機とシミュレーションのデモでSFT後、シミュレーションで強化学習しつつ実機データの補助損失で忘却を防ぐ協調学習フレームワークを提案し、実機卓上操作タスクで成功率と汎化性能を向上させた。
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: Liangzhi Shi, Shuaihang Chen, Feng Gao, Yinuo Chen, Kang Chen, Tonghe Zhang, Hongzhi Zang, Jiakai Zhou, Weinan Zhang, Chao Yu, Yu Wang
分類: cs.RO
原文アブストラクト
Simulation offers a scalable and low-cost way to enrich vision-language-action (VLA) training, reducing reliance on expensive real-robot demonstrations. However, most sim-real co-training methods rely on supervised fine-tuning (SFT), which treats simulation as a static source of demonstrations and does not exploit large-scale closed-loop interaction. Consequently, real-world gains and generalization are often limited. In this paper, we propose an RL-based sim-real Co-training (RL-Co) framework that leverages interactive simulation while preserving real-world capabilities. Our method follows a generic two-stage design: we first warm-start the policy with SFT on a mixture of real and simulated demonstrations, then fine-tune it with reinforcement learning in simulation while adding an auxiliary supervised loss on real-world data to anchor the policy and mitigate catastrophic forgetting. We evaluate our framework on four real-world tabletop manipulation tasks using two representative VLA architectures, OpenVLA and $\pi_{0.5}$, and observe consistent improvements over real-only fine-tuning and SFT-based co-training, including +24% real-world success on OpenVLA and +20% on $\pi_{0.5}$. Beyond higher success rates, RL co-training yields stronger generalization to unseen task variations and substantially improved real-world data efficiency, providing a practical and scalable pathway for leveraging simulation to enhance real-robot deployment.
