The Implementation of Asynchronous Advantage Actor-Critic with Stigmergy in Network-assisted Multi-agent System

被引：0

作者：

Chen, Kun ^{[1
]}

Li, Rongpeng ^{[1
]}

Zhao, Zhifeng ^{[2
]}

Zhang, Honggang ^{[1
]}

机构：

[1] Zhejiang Univ, Hangzhou, Peoples R China

[2] Zhejiang Lab, Hangzhou, Peoples R China

来源：

2020 12TH INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS AND SIGNAL PROCESSING (WCSP) | 2020年

基金：

中国国家自然科学基金; 国家重点研发计划;

关键词：

multi-agent system; stigmergy mechanism; digital pheromones; deep reinforcement learning; KHEPERA IV robots;

D O I：

10.1109/wcsp49889.2020.9299839

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Multi-agent system (MAS) needs to mobilize multiple simple agents to complete complex tasks. However, it is difficult to coherently coordinate distributed agents by means of limited local information. In this paper, we propose a decentralized collaboration method named as "stigmergy" in network-assisted MAS, by exploiting digital pheromones (DP) as an indirect medium of communication and utilizing deep reinforcement learning (DRL) on top. Correspondingly, we implement an experimental platform, where KHEPERA IV robots form targeted specific shapes in a decentralized manner. Experimental results demonstrate the effectiveness and efficiency of the proposed method. Our platform could be conveniently extended to investigate the impact of network factors (e.g., latency, data rate, etc) on the level of collective intelligence.

引用

页码：1082 / 1087

页数：6

共 50 条

[1] A New Advantage Actor-Critic Algorithm For Multi-Agent Environments
Paczolay, Gabor
Harmati, Istvan
[J]. 2020 23RD IEEE INTERNATIONAL SYMPOSIUM ON MEASUREMENT AND CONTROL IN ROBOTICS (ISMCR), 2020,
[2] Multi-Agent Actor-Critic with Hierarchical Graph Attention Network
Ryu, Heechang
Shin, Hayong
Park, Jinkyoo
[J]. THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 7236 - 7243
[3] Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning
Xiao, Yuchen
Lyu, Xueguang
Amato, Christopher
[J]. 2021 INTERNATIONAL SYMPOSIUM ON MULTI-ROBOT AND MULTI-AGENT SYSTEMS (MRS), 2021, : 155 - 163
[4] Distributed Multi-Agent Approach for Achieving Energy Efficiency and Computational Offloading in MECNs Using Asynchronous Advantage Actor-Critic
Khan, Israr
Raza, Salman
Khan, Razaullah
Rehman, Waheed ur
Rahman, G. M. Shafiqur
Tao, Xiaofeng
[J]. ELECTRONICS, 2023, 12 (22)
[5] B -Level Actor-Critic for Multi-Agent Coordination
Zhang, Haifeng
Chen, Weizhe
Huang, Zeren
Li, Minne
Yang, Yaodong
Zhang, Weinan
Wang, Jun
[J]. THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 7325 - 7332
[6] Divergence-Regularized Multi-Agent Actor-Critic
Su, Kefan
Lu, Zongqing
[J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
[7] UAV Assisted Cooperative Caching on Network Edge Using Multi-Agent Actor-Critic Reinforcement Learning
Araf, Sadman
Saha, Adittya Soukarjya
Kazi, Sadia Hamid
Tran, Nguyen H. H.
Alam, Md. Golam Rabiul
[J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2023, 72 (02) : 2322 - 2337
[8] Asynchronous Advantage Actor-Critic with Double Attention Mechanisms
Ling, Xing-Hong
Li, Jie
Zhu, Fei
Liu, Quan
Fu, Yu-Chen
[J]. Jisuanji Xuebao/Chinese Journal of Computers, 2020, 43 (01): : 93 - 106
[9] Actor-Critic Algorithms for Constrained Multi-agent Reinforcement Learning
Diddigi, Raghuram Bharadwaj
Reddy, D. Sai Koti
Prabuchandran, K. J.
Bhatnagar, Shalabh
[J]. AAMAS '19: PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS, 2019, : 1931 - 1933
[10] Multi-Agent Natural Actor-Critic Reinforcement Learning Algorithms
Prashant Trivedi
Nandyala Hemachandra
[J]. Dynamic Games and Applications, 2023, 13 : 25 - 55

← 1 2 3 4 5 →