断続的観測下における欺瞞的政策のオンライン学習
Online Learning of Deceptive Policies under Intermittent Observation
監視が時々しか行われない状況で、観測時に監督者の期待に沿うように振る舞いつつ私的目的を達成する欺瞞的行動を、心の理論を活用したオンライン強化学習で獲得する手法を提案し、船舶・ドローンの実験で有効性を示した。
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: Gokul Puthumanaillam, Ram Padmanabhan, Jose Fuentes, Nicole Cruz, Paulo Padrao, Ruben Hernandez, Hao Jiang, William Schafer, Leonardo Bobadilla, Melkior Ornik
分類: cs.RO, cs.MA, cs.SY, eess.SY
原文アブストラクト
In supervisory control settings, autonomous systems are not monitored continuously. Instead, monitoring often occurs at sporadic intervals within known bounds. We study the problem of deception, where an agent pursues a private objective while remaining plausibly compliant with a supervisor's reference policy when observations occur. Motivated by the behavior of real, human supervisors, we situate the problem within Theory of Mind: the representation of what an observer believes and expects to see. We show that Theory of Mind can be repurposed to steer online reinforcement learning (RL) toward such deceptive behavior. We model the supervisor's expectations and distill from them a single, calibrated scalar -- the expected evidence of deviation if an observation were to happen now. This scalar combines how unlike the reference and current action distributions appear, with the agent's belief that an observation is imminent. Injected as a state-dependent weight into a KL-regularized policy improvement step within an online RL loop, this scalar informs a closed-form update that smoothly trades off self-interest and compliance, thus sidestepping hand-crafted or heuristic policies. In real-world, real-time hardware experiments on marine (ASV) and aerial (UAV) navigation, our ToM-guided RL runs online, achieves high return and success with observed-trace evidence calibrated to the supervisor's expectations.
