Reinforcement Schedules
Associative Learning
Multi-input and Multi-variable systems
Randomized Experiments
Generalization, Discrimination, and Extinction
Response Surface Methodology
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。
Huiting Liu1, Junyi Wei2, Kaiwen Zhu3
1School of Computer Science and Technology, Anhui University, Hefei, 230601, Anhui, China; Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, 230088, Anhui, China.
本研究引入了跨领域顺序推的多代理强化学习框架 (MARL4CDSR). 通过智能选择和跨域传输用户数据,MARL4CDSR增强了推,优于现有方法.
科学领域:
背景情况:
研究的目的:
主要方法:
主要成果:
结论: