Decision Making: P-value Method
Reinforcement
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
Observational Learning
Reinforcement Schedules
Collisions in Multiple Dimensions: Problem Solving
您也可能阅读
通过共同作者、期刊和引用图与本文相关的文章。
Updated: Sep 18, 2025

The HoneyComb Paradigm for Research on Collective Human Behavior
Published on: January 19, 2019
Kai Liu1, Tianxian Zhang1, Xiangliang Xu1
1School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, Sichuan, China.
新的多代理强化学习 (MARL) 方法Comix通过使用上下界限来改进因子值函数 (FVF) 的更新. 这种方法提高了复杂的MARL任务的学习效率.
科学领域:
背景情况:
研究的目的:
主要方法:
主要成果:
结论: