欺骗性 Bandit 问题：探索耦合与多智能体学习脆弱性

1. 12:00
   arXiv · Machine Learning Theory

   欺骗性 Bandit 问题：探索耦合与多智能体学习的脆弱性

   论文证明随机探索的独立性与隐私性对安全至关重要，对手可利用另一智能体探索的特权信息实施欺骗。在最小双人强单调设定下，欺骗者获得仅与受害者探索相关的泄露信号，通过将自身探索动作与该信息耦合，注入外部性并把学习动态导向新的稳态——欺骗性纳什均衡（DNE）。

Current heat 9·Comparable peak 10（Oct 8）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.