半教師ありクロスドメイン模倣学習
Semi-Supervised Cross-Domain Imitation Learning
少数の目標ドメインの専門家デモとラベルなしの不完全軌道のみを用いて、ドメイン間の状態行動マッピングを学習する半教師ありクロスドメイン模倣学習手法を提案し、MuJoCoとRobosuiteで安定かつデータ効率的な性能向上を示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Li-Min Chu, Kai-Siang Ma, Ming-Hong Chen, Ping-Chun Hsieh
分類: cs.LG, cs.RO
原文アブストラクト
Cross-domain imitation learning (CDIL) accelerates policy learning by transferring expert knowledge across domains, which is valuable in applications where the collection of expert data is costly. Existing methods are either supervised, relying on proxy tasks and explicit alignment, or unsupervised, aligning distributions without paired data, but often unstable. We introduce the Semi-Supervised CDIL (SS-CDIL) setting and propose the first algorithm for SS-CDIL with theoretical justification. Our method uses only offline data, including a small number of target expert demonstrations and some unlabeled imperfect trajectories. To handle domain discrepancy, we propose a novel cross-domain loss function for learning inter-domain state-action mappings and design an adaptive weight function to balance the source and target knowledge. Experiments on MuJoCo and Robosuite show consistent gains over the baselines, demonstrating that our approach achieves stable and data-efficient policy learning with minimal supervision. Our code is available at~ https://github.com/NYCU-RL-Bandits-Lab/CDIL.
