Integrate multi-agent simulation environment and multi-agent reinforcement learning (MARL) for real-world scenario

被引：0

作者：

Yeo, Sangho ^{[1
]}

Lee, Seungjun ^{[2
]}

Choi, Boreum ^{[3
]}

Oh, Sangyoon ^{[1
]}

机构：

[1] Ajou Univ, Dept Comp Engn, Suwon, South Korea

[2] Ajou Univ, Dept Software, Suwon, South Korea

[3] Ajou Univ, Dept English Linguist & Literature, Suwon, South Korea

来源：

11TH INTERNATIONAL CONFERENCE ON ICT CONVERGENCE: DATA, NETWORK, AND AI IN THE AGE OF UNTACT (ICTC 2020) | 2020年

关键词：

deep reinforcement learning; MARL; multi agent simulation;

D O I：

10.1109/ictc49870.2020.9289369

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Multi-agent deep reinforcement learning has made a great achievement in deep reinforcement learning through modeling a real-world scenario with multiple agents that communicate with a single environment. However, the test and validation of MARL model on the conventional multi-agent simulation are limited. In this study, we analyze an effective method to use a multi-agent simulation to test and validate multi-agent reinforcement learning models and methods as well as propose two requirements, an intuitive interface and the optimization of simulation, to achieve it.

引用

页码：523 / 525

页数：3