適応的勾配マスク敵対攻撃によるロボティクスにおける堅牢な深層強化学習
Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks
深層強化学習エージェントの脆弱性を狙う新しい敵対攻撃手法AGMRを提案し、重要な状態次元を動的に特定して摂動を集中させることで攻撃性能を高め、防御機構を通じてエージェントの堅牢性も向上させる。
著者: Zongyuan Zhang, Tianyang Duan, Zheng Lin, Dong Huang, Zihan Fang, Zekai Sun, Ling Xiong, Hongbin Liang, Heming Cui, Yong Cui, Yue Gao
分類: cs.LG, cs.AI, cs.NI, cs.RO
原文アブストラクト
Deep reinforcement learning (DRL) has emerged as a promising approach for robotic control, but its realworld deployment remains challenging due to its vulnerability to environmental perturbations. Existing white-box adversarial attack methods, adapted from supervised learning, fail to effectively target DRL agents as they overlook temporal dynamics and indiscriminately perturb all state dimensions, limiting their impact on long-term rewards. To address these challenges, we propose the Adaptive Gradient-Masked Reinforcement (AGMR) Attack, a white-box attack method that combines DRL with a gradient-based soft masking mechanism to dynamically identify critical state dimensions and optimize adversarial policies. AGMR selectively allocates perturbations to the most impactful state features and incorporates a dynamic adjustment mechanism to balance exploration and exploitation during training. Extensive experiments demonstrate that AGMR outperforms state-of-the-art adversarial attack methods in degrading the performance of the victim agent and enhances the victim agent's robustness through adversarial defense mechanisms.
