バッチ型能動選好学習による報酬関数の効率的学習
Batch Active Preference-Based Learning of Reward Functions
ユーザーへの選好質問をバッチで能動的に生成することで、少ないクエリと短い計算時間で報酬関数を学習するアルゴリズムを提案し、収束保証とロボティクスシミュレーション実験で有効性を示した。
著者: Erdem Bıyık, Dorsa Sadigh
分類: cs.LG, cs.AI, cs.RO, stat.ML
原文アブストラクト
Data generation and labeling are usually an expensive part of learning for robotics. While active learning methods are commonly used to tackle the former problem, preference-based learning is a concept that attempts to solve the latter by querying users with preference questions. In this paper, we will develop a new algorithm, batch active preference-based learning, that enables efficient learning of reward functions using as few data samples as possible while still having short query generation times. We introduce several approximations to the batch active learning problem, and provide theoretical guarantees for the convergence of our algorithms. Finally, we present our experimental results for a variety of robotics tasks in simulation. Our results suggest that our batch active learning algorithm requires only a few queries that are computed in a short amount of time. We then showcase our algorithm in a study to learn human users' preferences.
