预训练机器人策略的高效持续自适应：在线元学习适配器
Efficient Continual Adaptation of Pretrained Robotic Policy with Online Meta-Learned Adapters
AI总结：
针对预训练机器人策略持续自适应中任务间知识迁移受限的问题，提出在线元学习适配器（OMLA），通过新颖的元学习目标促进知识迁移，在模拟和真实环境中优于基线方法。
摘要：
持续自适应对于通用自主智能体至关重要。例如，一个预训练了多种技能的居家机器人仍需适应每个家庭特有的未见任务。受此启发，基于语言模型中的参数高效微调，先前工作探索了轻量级适配器来调整预训练策略，这些适配器能保留预训练阶段学到的特征并展现出良好的自适应性能。然而，这些方法将任务学习分开处理，限制了任务间的知识迁移。在本文中，我们提出在线元学习适配器（OMLA）。不同于直接应用适配器，OMLA通过一种新颖的元学习目标，促进从先前学到的任务向当前学习任务的知识迁移。在模拟和真实环境中的大量实验表明，与基线方法相比，OMLA能带来更好的自适应性能。项目链接：https://ricky-zhu.github.io/OMLA/。
英文摘要：
Continual adaptation is essential for general autonomous agents. For example, a household robot pretrained with a repertoire of skills must still adapt to unseen tasks specific to each household. Motivated by this, building upon parameter-efficient fine-tuning in language models, prior works have explored lightweight adapters to adapt pretrained policies, which can preserve learned features from the pretraining phase and demonstrate good adaptation performances. However, these approaches treat task learning separately, limiting knowledge transfer between tasks. In this paper, we propose Online Meta-Learned adapters (OMLA). Instead of applying adapters directly, OMLA can facilitate knowledge transfer from previously learned tasks to current learning tasks through a novel meta-learning objective. Extensive experiments in both simulated and real-world environments demonstrate that OMLA can lead to better adaptation performances compared to the baseline methods. The project link: https://ricky-zhu.github.io/OMLA/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
