Connected replicator dynamics and their control in a learning multi-agent system

被引：0

作者：

Kunigami, M ^{[1
]}

Terano, T ^{[1
]}

机构：

[1] GSSM Tsukuba Univ, Bunkyo Ku, Tokyo, Japan

来源：

INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING | 2003年 / 2690卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper analyzes complex behaviors of a multi-agent system, which consists of interacting agents with evolutionally learning capabilities. The interaction and learning of agents are modeled using Connected Replicator Dynamics expanded from the evolutional game theory. The dynamic systems show various behavioral and decision changes the including bifurcation of chaos in physics. The main contributions of this paper are as follows: (1) In the multi-agent system, the emergence of chaotic behaviors is general and essential, although each agent does not have chaotic properties; (2) However, simple controlling agent with the KISS (Keep-It-Simple-Stupid) principle or a sheepdog agent domesticates the complex behavior.

引用

页码：18 / 26

页数：9

共 50 条

[31] Hybrid Multi-Agent Based Resilient Control for EV Connected Micro Grid System
Hintz, Andrew S.
Prasanna, Udupi. R.
Rajashekara, Kaushik
[J]. 2014 IEEE TRANSPORTATION ELECTRIFICATION CONFERENCE AND EXPO (ITEC), 2014,
[32] Multi-agent reinforcement learning for character control
Li, Cheng
Fussell, Levi
Komura, Taku
[J]. VISUAL COMPUTER, 2021, 37 (12): : 3115 - 3123
[33] Iterative Learning Control of Multi-agent Systems
Pakshin, Pavel
Emelianova, Julia
[J]. 2017 10TH INTERNATIONAL WORKSHOP ON MULTIDIMENSIONAL (ND) SYSTEMS (NDS), 2017,
[34] Multi-agent reinforcement learning for character control
Cheng Li
Levi Fussell
Taku Komura
[J]. The Visual Computer, 2021, 37 : 3115 - 3123
[35] A novel multi-agent Q-learning algorithm in cooperative multi-agent system
Ou, HT
Zhang, WD
Zhang, WY
Xu, XM
[J]. PROCEEDINGS OF THE 3RD WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-5, 2000, : 272 - 276
[36] ON PESONALISED MULTI-AGENT LEARNING SYSTEM: LEARNING OUTCOMES ASSESSMENT AGENT
Melesko, Jaroslav
[J]. 10TH INTERNATIONAL CONFERENCE OF EDUCATION, RESEARCH AND INNOVATION (ICERI2017), 2017, : 3892 - 3899
[37] Experimental Study on Decentralized Concurrent Learning for Multi-Agent System with Complex Dynamics
Fei, Ting
Chen, Xin
Wu, Min
Wang, Chi
[J]. PROCEEDINGS OF THE 36TH CHINESE CONTROL CONFERENCE (CCC 2017), 2017, : 8373 - 8378
[38] Graph neural network and reinforcement learning for multi-agent cooperative control of connected autonomous vehicles
Chen, Sikai
Dong, Jiqian
Ha, Paul
Li, Yujie
Labi, Samuel
[J]. COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2021, 36 (07) : 838 - 857
[39] Learning process: Multi-Agent Tutoring System
Perez Morinigo, Manuel
Merchan Montero, Victor
Martin Perez, Jose Luis
[J]. ADCAIJ-ADVANCES IN DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE JOURNAL, 2019, 8 (01): : 5 - 12
[40] An improved learning approach in Multi-agent system
Liang, Jun
Cheng, Xian-Yi
[J]. PROCEEDINGS OF 2008 INTERNATIONAL COLLOQUIUM ON ARTIFICIAL INTELLIGENCE IN EDUCATION, 2008, : 6 - 10

← 1 2 3 4 5 →