オンラインメタ学習アダプタによる事前学習済みロボット方策の効率的な継続適応
Efficient Continual Adaptation of Pretrained Robotic Policy with Online Meta-Learned Adapters
事前学習済みロボット方策に軽量アダプタをオンラインメタ学習で組み込み、過去のタスク知識を新規タスクへ転移させて継続適応性能を高める手法を提案。
著者: Ruiqi Zhu, Endong Sun, Guanhe Huang, Oya Celiktutan
分類: cs.RO, cs.AI
原文アブストラクト
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/.
