もつれ解き木表現によるニューラルポリシーの解釈
Interpreting Neural Policies with Disentangled Tree Representations
決定木を用いてロボット学習ポリシーの潜在表現をもつれ解きし、その解釈性を集中度・相互情報量・モジュール性の観点から定量評価する手法を提案した。
著者: Tsun-Hsuan Wang, Wei Xiao, Tim Seyde, Ramin Hasani, Daniela Rus
分類: cs.LG, cs.AI, cs.NE, cs.RO, stat.ML
原文アブストラクト
The advancement of robots, particularly those functioning in complex human-centric environments, relies on control solutions that are driven by machine learning. Understanding how learning-based controllers make decisions is crucial since robots are often safety-critical systems. This urges a formal and quantitative understanding of the explanatory factors in the interpretability of robot learning. In this paper, we aim to study interpretability of compact neural policies through the lens of disentangled representation. We leverage decision trees to obtain factors of variation [1] for disentanglement in robot learning; these encapsulate skills, behaviors, or strategies toward solving tasks. To assess how well networks uncover the underlying task dynamics, we introduce interpretability metrics that measure disentanglement of learned neural dynamics from a concentration of decisions, mutual information and modularity perspective. We showcase the effectiveness of the connection between interpretability and disentanglement consistently across extensive experimental analysis.
