反事実的軌跡による強化学習ポリシーの説明
Explaining Reinforcement Learning Policies through Counterfactual Trajectories
強化学習エージェントの分布シフト下での振る舞いを、多様な未見状態へ誘導した軌跡で可視化し、人間が検証しやすくする手法を提案した。
著者: Julius Frost, Olivia Watkins, Eric Weiner, Pieter Abbeel, Trevor Darrell, Bryan Plummer, Kate Saenko
分類: cs.LG, cs.AI, cs.HC, cs.RO
原文アブストラクト
In order for humans to confidently decide where to employ RL agents for real-world tasks, a human developer must validate that the agent will perform well at test-time. Some policy interpretability methods facilitate this by capturing the policy's decision making in a set of agent rollouts. However, even the most informative trajectories of training time behavior may give little insight into the agent's behavior out of distribution. In contrast, our method conveys how the agent performs under distribution shifts by showing the agent's behavior across a wider trajectory distribution. We generate these trajectories by guiding the agent to more diverse unseen states and showing the agent's behavior there. In a user study, we demonstrate that our method enables users to score better than baseline methods on one of two agent validation tasks.
