報酬関数を人間に説明して円滑な人とロボットの協働を実現する
Explaining Reward Functions to Humans for Better Human-Robot Collaboration
報酬説明手法を情報モダリティで分類し、人間の報酬理解を評価する手法群とドメイン複雑さの4軸を提案、多様な説明手法の有効性を比較する実験計画を示した論文。
著者: Lindsay Sanneman, Julie Shah
分類: cs.RO, cs.AI, cs.HC
原文アブストラクト
Explainable AI techniques that describe agent reward functions can enhance human-robot collaboration in a variety of settings. One context where human understanding of agent reward functions is particularly beneficial is in the value alignment setting. In the value alignment context, an agent aims to infer a human's reward function through interaction so that it can assist the human with their tasks. If the human can understand where gaps exist in the agent's reward understanding, they will be able to teach more efficiently and effectively, leading to quicker human-agent team performance improvements. In order to support human collaborators in the value alignment setting and similar contexts, it is first important to understand the effectiveness of different reward explanation techniques in a variety of domains. In this paper, we introduce a categorization of information modalities for reward explanation techniques, suggest a suite of assessment techniques for human reward understanding, and introduce four axes of domain complexity. We then propose an experiment to study the relative efficacy of a broad set of reward explanation techniques covering multiple modalities of information in a set of domains of varying complexity.
