条件付きエネルギーベースモデルによる暗黙的方策:理論と実践のギャップ
Conditional Energy-Based Models for Implicit Policies: The Gap between Theory and Practice
行動クローニングの方策を暗黙的に表現する条件付きエネルギーベースモデル(EBM)について、理論と実践の乖離を整理し、無条件EBMとの違いや最大相互情報量原理の重要性を指摘した。
著者: Duy-Nguyen Ta, Eric Cousineau, Huihua Zhao, Siyuan Feng
分類: cs.RO, cs.LG
原文アブストラクト
We present our findings in the gap between theory and practice of using conditional energy-based models (EBM) as an implicit representation for behavior-cloned policies. We also clarify several subtle, and potentially confusing, details in previous work in an attempt to help future research in this area. We point out key differences between unconditional and conditional EBMs, and warn that blindly applying training methods for one to the other could lead to undesirable results that do not generalize well. Finally, we emphasize the importance of the Maximum Mutual Information principle as a necessary condition to achieve good generalization in conditional EBMs as implicit models for regression tasks.
