Multi-Agent Reinforcement Learning with Shared Policy for Cloud Quota Management Problem

被引：0

作者：

Cheng, Tong ^{[1
]}

Dong, Hang ^{[1
]}

Wang, Lu ^{[1
]}

Qiao, Bo ^{[1
]}

Qin, Si ^{[1
]}

Lin, Qingwei ^{[1
]}

Zhang, Dongmei ^{[1
]}

Rajmohan, Saravan ^{[2
]}

Moscibroda, Thomas ^{[3
]}

机构：

[1] Microsoft Res, Redmond, WA 98052 USA

[2] Microsoft 365, Redmond, WA USA

[3] Microsoft Azure, Redmond, WA USA

来源：

COMPANION OF THE WORLD WIDE WEB CONFERENCE, WWW 2023 | 2023年

关键词：

reinforcement learning; cloud computing; multi-agent system; EFFICIENCY-FAIRNESS TRADEOFF; RESOURCE-ALLOCATION;

D O I：

10.1145/3543873.3584634

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Quota is often used in resource allocation and management scenarios to prevent abuse of resource and increase the efficiency of resource utilization. Quota management is usually fulfilled with a set of rules maintained by the system administrator. However, maintaining these rules usually needs deep domain knowledge. Moreover, arbitrary rules usually cannot guarantee both high resource utilization and fairness at the same time. In this paper, we propose a reinforcement learning framework to automatically respond to quota requests in cloud computing platforms with distinctive usage characteristics for users. Extensive experimental results have demonstrated the superior performance of our framework on achieving a great trade-of between efficiency and fairness.

引用

页码：391 / 395

页数：5

共 50 条

[1] Celebrating Diversity in Shared Multi-Agent Reinforcement Learning
Li, Chenghao
Wang, Tonghan
Wu, Chengjie
Zhao, Qianchuan
Yang, Jun
Zhang, Chongjie
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
[2] Decentralized Multi-agent Reinforcement Learning with Shared Actions
Mishra, Rajesh K.
Vasal, Deepanshu
Vishwanath, Sriram
[J]. 2021 55TH ANNUAL CONFERENCE ON INFORMATION SCIENCES AND SYSTEMS (CISS), 2021,
[3] Reinforcement learning for multi-agent patrol policy
Lab. of Complex Systems and Intelligence Sciences, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
[J]. Proc. IEEE Int. Conf. Cognitive Informatics, ICCI, (530-535):
[4] TEAM POLICY LEARNING FOR MULTI-AGENT REINFORCEMENT LEARNING
Cassano, Lucas
Alghunaim, Sulaiman A.
Sayed, Ali H.
[J]. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 3062 - 3066
[5] Multi-agent Reinforcement Learning in Network Management
Bagnasco, Ricardo
Serrat, Joan
[J]. SCALABILITY OF NETWORKS AND SERVICES, PROCEEDINGS, 2009, 5637 : 199 - 202
[6] Uncertainty modified policy for multi-agent reinforcement learning
Zhao, Xinyu
Liu, Jianxiang
Wu, Faguo
Zhang, Xiao
Wang, Guojian
[J]. APPLIED INTELLIGENCE, 2024, 54 (22) : 12020 - 12034
[7] Learning of Communication Codes in Multi-Agent Reinforcement Learning Problem
Kasai, Tatsuya
Tenmoto, Hiroshi
Kamiya, Akimoto
[J]. 2008 IEEE CONFERENCE ON SOFT COMPUTING IN INDUSTRIAL APPLICATIONS SMCIA/08, 2009, : 1 - +
[8] Cooperative Multi-agent Reinforcement Learning for Inventory Management
Khirwar, Madhav
Gurumoorthy, Karthik S.
Jain, Ankit Ajit
Manchenahally, Shantala
[J]. MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES: APPLIED DATA SCIENCE AND DEMO TRACK, ECML PKDD 2023, PT VI, 2023, 14174 : 619 - 634
[9] Multi-agent hierarchical reinforcement learning for energy management
Jendoubi, Imen
Bouffard, Francois
[J]. APPLIED ENERGY, 2023, 332
[10] Multi-Agent Reinforcement Learning
Stankovic, Milos
[J]. 2016 13TH SYMPOSIUM ON NEURAL NETWORKS AND APPLICATIONS (NEUREL), 2016, : 43 - 43

← 1 2 3 4 5 →