アンサンブルモデル予測型安全認証を用いた強化学習
Reinforcement Learning with Ensemble Model Predictive Safety Certification
安全制御器のオフラインデータのみを用い、モデルベース強化学習とチューブ型モデル予測制御を組み合わせて行動を補正し、制約違反を大幅に削減する手法を提案。
著者: Sven Gronauer, Tom Haider, Felippe Schmoeller da Roza, Klaus Diepold
分類: cs.LG, cs.RO
原文アブストラクト
Reinforcement learning algorithms need exploration to learn. However, unsupervised exploration prevents the deployment of such algorithms on safety-critical tasks and limits real-world deployment. In this paper, we propose a new algorithm called Ensemble Model Predictive Safety Certification that combines model-based deep reinforcement learning with tube-based model predictive control to correct the actions taken by a learning agent, keeping safety constraint violations at a minimum through planning. Our approach aims to reduce the amount of prior knowledge about the actual system by requiring only offline data generated by a safe controller. Our results show that we can achieve significantly fewer constraint violations than comparable reinforcement learning methods.
