用专家混合模型让机器人学会多样技能，避免多任务干扰。
Learning Diverse Skills for Behavior Models with Mixture of Experts
- 用能量模型定义专家专属观察分布，实现技能专业化。
- 在多个真实机器人任务上表现优于当前最优基线。
- 微调新任务时数据效率高，已学知识可复用。
模仿学习在机器人操作中通过大规模人类示范展现强大性能。然而现有模型在单任务上表现优异，实际多任务场景下性能下降，因任务间干扰导致性能平均化。为此，我们提出基于专家混合的多样化行为建模方法（Di-BM），将每个专家关联至特定的观测分布，使专家专注于观测空间的子区域。具体地，采用基于能量的模型表示专家特有的观测分布，并与对应的动作模型联合训练。该方法可无缝集成至标准模仿学习框架，具备即插即用特性。在多个真实世界机器人操作任务上的大量实验表明，Di-BM显著超越现有最优基线。此外，在新任务上进行微调时展现出更优的数据效率和专家知识的可复用性。代码开源：https://github.com/robotnav-bot/Di-BM。
原文摘要 · Abstract (English)
Imitation learning has demonstrated strong performance in robotic manipulation by learning from large-scale human demonstrations. While existing models excel at single-task learning, it is observed in practical applications that their performance degrades in the multi-task setting, where interference across tasks leads to an averaging effect. To address this issue, we propose to learn diverse skills for behavior models with Mixture of Experts, referred to as Di-BM. Di-BM associates each expert with a distinct observation distribution, enabling experts to specialize in sub-regions of the observation space. Specifically, we employ energy-based models to represent expert-specific observation distributions and jointly train them alongside the corresponding action models. Our approach is plug-and-play and can be seamlessly integrated into standard imitation learning methods. Extensive experiments on multiple real-world robotic manipulation tasks demonstrate that Di-BM significantly outperforms state-of-the-art baselines. Moreover, fine-tuning the pretrained Di-BM on novel tasks exhibits superior data efficiency and the reusable of expert-learned knowledge. Code is available at https://github.com/robotnav-bot/Di-BM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。