安全性を競技力へ:安全フィルタ付き強化学習による搾取されにくいロボット方策
Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning
競技タスク向けに、安全フィルタを敵対的RLで学習してからタスク方策を訓練する2段階フレームワークS2Cを提案し、安全性と競技性能・非搾取性を両立させた。
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: Ruihan Wu, Rui Yang, Donggeon David Oh, Duy Nguyen, Haimin Hu
分類: cs.RO, cs.AI, cs.LG, eess.SY
原文アブストラクト
Robots deployed for competitive tasks must outmaneuver their opponents without sacrificing safety. Existing approaches, including safe reinforcement learning (RL), train a single policy to achieve task success and avoid failures simultaneously. This coupling can complicate training and leave the learned policy exploitable by deliberate attacks. We propose Safety to Competence (S2C), a two-stage RL framework that separates safety synthesis from competitive task learning. We formulate competitive interactions as safety-critical Markov games and prove that perfect filtering preserves policy non-exploitability when all players commit to safe maneuvers. S2C learns a robust safety filter via adversarial RL, embeds it in the environment during task policy training, and retains the same filter at deployment. In simulated touchdown games, S2C outperforms eight safe RL baselines, achieving the highest win rate and Elo rating, and the lowest exploitability. Hardware stress tests against a human opponent confirm S2C's competence.