滑らかな安全性構造化ポリシー合成による安全なオンライン学習
Safe Online Learning via Smooth Safety-Structured Policy Composition
安全性監視と介入を行動生成に統合したポリシーアーキテクチャAutoSafeを提案し、性能追求と安全確保の行動を滑らかに切り替えることで、学習の滑らかさを保ちつつ安全性を確保する。
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: Hongpeng Cao, Liqun Zhao, Yuliang Gu, Naira Hovakimyan, Lui Sha, Marco Caccamo
分類: cs.LG, cs.RO
原文アブストラクト
Safe online reinforcement learning requires policies to respect safety constraints while maintaining smooth optimization dynamics. Existing approaches typically rely on either strict safety enforcement via action interventions, which introduce discontinuities in system interaction and learning, or soft safety constraint formulations, which preserve smooth learning but provide limited safety assurance. We propose AutoSafe, a safety-aware policy architecture that integrates structured safety monitoring and intervention directly into the action generation process. This design enables smooth, risk-dependent transitions between performance-driven and safety-preserving behaviors, resulting in continuous online interaction and learning dynamics. Empirical results across a suite of continuous-control benchmarks demonstrate strong safety enforcement without sacrificing learning smoothness. We further validate AutoSafe on a physical cart-pole system, highlighting its practical effectiveness for safe online learning in the real world.
