言語情報を活用した家庭内活動の転移学習
Language-Informed Transfer Learning for Embodied Household Activities
家庭内タスクの転移学習において、状態と目標のテキスト表現を言語モデルで埋め込み、意味的類似度に基づいて類似タスクを選択することで、新規タスクの学習を効率化する手法を提案した。
著者: Yuqian Jiang, Qiaozi Gao, Govind Thattai, Gaurav Sukhatme
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
For service robots to become general-purpose in everyday household environments, they need not only a large library of primitive skills, but also the ability to quickly learn novel tasks specified by users. Fine-tuning neural networks on a variety of downstream tasks has been successful in many vision and language domains, but research is still limited on transfer learning between diverse long-horizon tasks. We propose that, compared to reinforcement learning for a new household activity from scratch, home robots can benefit from transferring the value and policy networks trained for similar tasks. We evaluate this idea in the BEHAVIOR simulation benchmark which includes a large number of household activities and a set of action primitives. For easy mapping between state spaces of different tasks, we provide a text-based representation and leverage language models to produce a common embedding space. The results show that the selection of similar source activities can be informed by the semantic similarity of state and goal descriptions with the target task. We further analyze the results and discuss ways to overcome the problem of catastrophic forgetting.
