オンライン力学学習による安全かつ準最適な制御
Safe and Near-Optimal Control with Online Dynamics Learning
未知の力学系において、安全性を保証しながらオンラインで力学モデルを学習し、準最適な性能を達成する制御手法を提案した論文。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Manish Prajapat, Johannes Köhler, Melanie N. Zeilinger, Andreas Krause
分類: eess.SY, cs.LG, cs.RO, cs.SY, math.DS, math.OC
原文アブストラクト
Achieving both optimality and safety under unknown system dynamics is a central challenge in real-world deployment of agents. To address this, we introduce a notion of maximum safe dynamics learning, where sufficient exploration is performed within the space of safe policies. Our method executes $\textit{pessimistically}$ safe policies while $\textit{optimistically}$ exploring informative states and, despite not reaching them due to model uncertainty, ensures continuous online learning of dynamics. The framework achieves first-of-its-kind results: learning the dynamics model sufficiently $-$ up to an arbitrary small tolerance (subject to noise) $-$ in a finite time, while ensuring provably safe operation throughout with high probability and without requiring resets. Building on this, we propose an algorithm to maximize rewards while learning the dynamics $\textit{only to the extent needed}$ to achieve close-to-optimal performance. Unlike typical reinforcement learning (RL) methods, our approach operates online in a non-episodic setting and ensures safety throughout the learning process. We demonstrate the effectiveness of our approach in challenging domains such as autonomous car racing and drone navigation under aerodynamic effects $-$ scenarios where safety is critical and accurate modeling is difficult.
