再構成誤差に基づく不確実性推定でモデルベース制御と能動探索を改善
Improving Model-Based Control and Active Exploration with Reconstruction Uncertainty Optimization
モデルの予測誤差から不確実性を見積もり、自信のある予測を選んで制御性能を高めるとともに、不確実性の高い軌道を計画して効率的に環境を探索・学習する手法を提案した。
著者: Norman Di Palo, Harri Valpola
分類: cs.LG, cs.AI, cs.NE, cs.RO, stat.ML
原文アブストラクト
Model based predictions of future trajectories of a dynamical system often suffer from inaccuracies, forcing model based control algorithms to re-plan often, thus being computationally expensive, suboptimal and not reliable. In this work, we propose a model agnostic method for estimating the uncertainty of a model?s predictions based on reconstruction error, using it in control and exploration. As our experiments show, this uncertainty estimation can be used to improve control performance on a wide variety of environments by choosing predictions of which the model is confident. It can also be used for active learning to explore more efficiently the environment by planning for trajectories with high uncertainty, allowing faster model learning.
