摂動下で頑健なニューラルLyapunov障壁証明書の形式的合成
Formal Synthesis of Certifiably Robust Neural Lyapunov-Barrier Certificates
システムダイナミクスの有界な摂動に対して安全性・安定性の保証を維持する頑健なニューラルLyapunov障壁証明書を、敵対的訓練とLipschitz正則化で学習する手法を提案し、倒立振子と2Dドッキングで有効性を示した。
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: Chengxiao Wang, Haoze Wu, Gagandeep Singh
分類: cs.LG, cs.AI, cs.RO, cs.SY, eess.SY
原文アブストラクト
Neural Lyapunov and barrier certificates have recently been used as powerful tools for verifying the safety and stability properties of deep reinforcement learning (RL) controllers. However, existing methods offer guarantees only under fixed ideal unperturbed dynamics, limiting their reliability in real-world applications where dynamics may deviate due to uncertainties. In this work, we study the problem of synthesizing \emph{robust neural Lyapunov barrier certificates} that maintain their guarantees under perturbations in system dynamics. We formally define a robust Lyapunov barrier function and specify sufficient conditions based on Lipschitz continuity that ensure robustness against bounded perturbations. We propose practical training objectives that enforce these conditions via adversarial training, Lipschitz neighborhood bound, and global Lipschitz regularization. We validate our approach in two practically relevant environments, Inverted Pendulum and 2D Docking. The former is a widely studied benchmark, while the latter is a safety-critical task in autonomous systems. We show that our methods significantly improve both certified robustness bounds (up to $4.6$ times) and empirical success rates under strong perturbations (up to $2.4$ times) compared to the baseline. Our results demonstrate effectiveness of training robust neural certificates for safe RL under perturbations in dynamics.
