非エピソード型強化学習によるロボット操作のベンチマークCRONOS
CRONOS: Benchmarking Non-Episodic Reinforcement Learning for Robotic Manipulation
シーンリセットを頻繁に行わない非エピソード設定でVLAモデルを強化学習ファインチューニングするためのシミュレーションベンチマークを構築し、素朴なファインチューニングの失敗要因とその緩和策、長期的操作や未知配置への汎化向上を示した。
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: Po-Yi Wu, Djengo Cyun-Jyun Fang, Dian Cheng, Tsung-Wei Ke
分類: cs.RO, cs.LG
原文アブストラクト
Reinforcement learning (RL) is promising for adapting robot policies to unstructured real-world environments. However, standard RL pipelines rely on episodic training with frequent scene resets, which is impractical for real-world deployment due to the need for substantial human intervention. While prior work has studied non-episodic RL in relatively small policies trained from scratch, its behavior when fine-tuning modern large-scale pre-trained vision-language-action (VLA) models remains underexplored. In this work, we introduce CRONOS, a simulation benchmark for RL fine-tuning of VLAs under non-episodic scene resets. CRONOS leverages high-fidelity physics simulators and adopts shared-scene multi-task settings. Using CRONOS, we show that naively fine-tuning pre-trained policies fails in non-episodic settings due to shifts in object configurations and end-effector poses; however, these challenges can be mitigated through targeted reset allocation and by addressing biases in pre-trained models. Moreover, we find that non-episodic training enhances long-horizon manipulation and improves generalization to previously unseen object configurations and task sequences. Project page: https://embodiedai-ntu.github.io/cronos/