学習された分離目標空間の好奇心駆動型探索
Curiosity Driven Exploration of Learned Disentangled Goal Spaces
分離された目標空間表現を用いることで、複雑な環境での好奇心駆動型探索の性能が向上し、学習進捗をモジュール的に活用して独立制御可能な特徴を発見できることを示した論文。
著者: Adrien Laversanne-Finot, Alexandre Péré, Pierre-Yves Oudeyer
分類: cs.LG, cs.AI, cs.NE, cs.RO, stat.ML
原文アブストラクト
Intrinsically motivated goal exploration processes enable agents to autonomously sample goals to explore efficiently complex environments with high-dimensional continuous actions. They have been applied successfully to real world robots to discover repertoires of policies producing a wide diversity of effects. Often these algorithms relied on engineered goal spaces but it was recently shown that one can use deep representation learning algorithms to learn an adequate goal space in simple environments. However, in the case of more complex environments containing multiple objects or distractors, an efficient exploration requires that the structure of the goal space reflects the one of the environment. In this paper we show that using a disentangled goal space leads to better exploration performances than an entangled goal space. We further show that when the representation is disentangled, one can leverage it by sampling goals that maximize learning progress in a modular manner. Finally, we show that the measure of learning progress, used to drive curiosity-driven exploration, can be used simultaneously to discover abstract independently controllable features of the environment.
