使

Shun Kotoku1, Takatomo Mihana1, André Röhm1

  • 1The University of Tokyo, Department of Information Physics and Computing, Graduate School of Information Science and Technology, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan.

Physical review. E
|February 7, 2025
PubMed
概括

本研究介绍了一种用于多代理强化学习 (MARL) 的新型光子算法,以解决竞争性多武装强盗 (CMAB) 问题,使得在没有直接信息共享的情况下进行合作决策.