ベイズニューラルネットワークによる複数環境下での不確実性を考慮した模倣学習
Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks
ベイズニューラルネットワークの不確実性を用いて、学習済みロボット制御器が性能低下する状況を検出し、必要な時だけ追加データを要求することでデータ効率を高める手法を提案した。
著者: Sanjay Thakur, Herke van Hoof, Juan Camilo Gamboa Higuera, Doina Precup, David Meger
分類: cs.RO, cs.LG
原文アブストラクト
Diversity of environments is a key challenge that causes learned robotic controllers to fail due to the discrepancies between the training and evaluation conditions. Training from demonstrations in various conditions can mitigate---but not completely prevent---such failures. Learned controllers such as neural networks typically do not have a notion of uncertainty that allows to diagnose an offset between training and testing conditions, and potentially intervene. In this work, we propose to use Bayesian Neural Networks, which have such a notion of uncertainty. We show that uncertainty can be leveraged to consistently detect situations in high-dimensional simulated and real robotic domains in which the performance of the learned controller would be sub-par. Also, we show that such an uncertainty based solution allows making an informed decision about when to invoke a fallback strategy. One fallback strategy is to request more data. We empirically show that providing data only when requested results in increased data-efficiency.
