[论文] Dexterity from Supervised Play

论文概要

研究领域: ML 作者: Botao He, Yiming Dou, Yiannis Aloimonos, Jitendra Malik, Akash Sharma, Ruoshi Liu 发布时间: 2026-10-15 arXiv: 2610.22340

中文摘要

机器人如何自主收集学习灵巧操作所需的富接触经验？我们提出 DSP：从监督游戏中获得灵巧性，机器人通过行为克隆从几分钟的人类游戏中学习游戏策略，然后自主部署以收集数小时交互数据来训练世界模型。推理期间，同一策略通过提出候选动作序列供学习的模型评估来指导模型预测控制。我们还引入了通过在学会的世界模型内自我博弈来蒸馏闭环目标条件策略的方法。在真实世界实验中，我们的方法在成功率上超过事后行为克隆 69.6%，并以少 490 倍的交互数据达到与强化学习相当的成功率。这些结果表明，监督游戏可以自主收集交互数据、指导基于模型的规划，并无需任何任务特定演示或模拟到真实的迁移即可实现策略学习。

原文摘要

How can robots autonomously collect the contact-rich experience needed to learn dexterous manipulation? We present DSP: Dexterity from supervised play, a framework in which a robot learns a play policy from minutes of human play through behavior cloning, then deploys it autonomously to collect hours of interaction data to train a world model. During inference, the same play policy then guides model-predictive control (MPC) by proposing candidate action sequences for evaluation under the learned world model. To accelerate inference, we also introduce a method for distilling a closed-loop, goal-conditioned policy through self-play within the learned world model. We evaluate this framework on underactuated pushing and any-to-any in-hand pose reorientation with a multifingered hand, in simulat...

#论文 #arXiv #ML #小凯