对抗鲁棒联邦Q学习算法Robust Async-Fed-Q

1. 12:00
   arXiv · Machine Learning Theory

   从不可靠轨迹中学习：对抗鲁棒的联邦 Q-Learning

   论文研究多智能体在共享 MDP 中通过中央服务器协作学习最优状态-动作值函数，并提出 Robust Async-Fed-Q 算法，结合智能体端对方差缩减的 Bellman 最优算子估计与服务器端鲁棒聚合。

Current heat 9·Comparable peak 10（Oct 7）·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.