答えやすい質問で効率的に報酬を学ぶ手法
Asking Easy Questions: A User-Friendly Approach to Active Reward Learning
人間が答えやすい質問を選ぶことで、ロボットが報酬関数をより速く学習できる能動的報酬学習の手法を提案した論文。
著者: Erdem Bıyık, Malayandi Palan, Nicholas C. Landolfi, Dylan P. Losey, Dorsa Sadigh
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Robots can learn the right reward function by querying a human expert. Existing approaches attempt to choose questions where the robot is most uncertain about the human's response; however, they do not consider how easy it will be for the human to answer! In this paper we explore an information gain formulation for optimally selecting questions that naturally account for the human's ability to answer. Our approach identifies questions that optimize the trade-off between robot and human uncertainty, and determines when these questions become redundant or costly. Simulations and a user study show our method not only produces easy questions, but also ultimately results in faster reward learning.
