能動的選好学習のための反事実推論と環境設計
Counterfactual Reasoning and Environment Design for Active Preference Learning
ロボットが人間の選好を効率的に学ぶため、環境設計と軌道選択を同時最適化し、反事実推論で多様で情報量の多い軌道を生成する手法CREDを提案した。
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: Yi-Shiuan Tung, Bradley Hayes, Alessandro Roncone
分類: cs.RO
原文アブストラクト
For effective real-world deployment, robots should adapt to human preferences, such as balancing distance, time, and safety in delivery routing. Active preference learning (APL) learns human reward functions by presenting trajectories for ranking. However, existing methods often struggle to explore the full trajectory space and fail to identify informative queries, particularly in long-horizon tasks. We propose CRED, a trajectory generation method for APL that improves reward estimation by jointly optimizing environment design and trajectory selection. CRED "imagines" new scenarios through environment design and uses counterfactual reasoning -- by sampling rewards from its current belief and asking "What if this reward were the true preference?" -- to generate a diverse and informative set of trajectories for ranking. Experiments in GridWorld and real-world navigation using OpenStreetMap data show that CRED improves reward learning and generalizes effectively across different environments.
