ハイパーネットワークによる継続的模倣学習における最適化手法・初期化・アーキテクチャの影響調査
Effect of Optimizer, Initializer, and Architecture of Hypernetworks on Continual Learning from Demonstration
ロボットが人間の実演から連続的に動作スキルを学ぶCLfDにおいて、ハイパーネットワークの最適化器・初期化・ネットワーク構造が学習性能に与える影響を実験的に調査した。
著者: Sayantan Auddy, Sebastian Bergner, Justus Piater
分類: cs.RO, cs.LG
原文アブストラクト
In continual learning from demonstration (CLfD), a robot learns a sequence of real-world motion skills continually from human demonstrations. Recently, hypernetworks have been successful in solving this problem. In this paper, we perform an exploratory study of the effects of different optimizers, initializers, and network architectures on the continual learning performance of hypernetworks for CLfD. Our results show that adaptive learning rate optimizers work well, but initializers specially designed for hypernetworks offer no advantages for CLfD. We also show that hypernetworks that are capable of stable trajectory predictions are robust to different network architectures. Our open-source code is available at https://github.com/sebastianbergner/ExploringCLFD.
