Balancing Performance and Cost for Two-Hop Cooperative Communications: Stackelberg Game and Distributed Multi-Agent Reinforcement Learning

被引:0
|
作者
Geng, Yuanzhe [1 ]
Liu, Erwu [1 ]
Ni, Wei [2 ]
Wang, Rui [3 ]
Liu, Yan [1 ]
Xu, Hao [1 ]
Cai, Chen [4 ]
Jamalipour, Abbas [5 ]
机构
[1] Tongji Univ, Coll Elect & Informat Engn, Shanghai 201804, Peoples R China
[2] Commonwealth Sci & Ind Res Org, Data61, Marsfield, NSW 2122, Australia
[3] Tongji Univ, Coll Elect & Informat Engn, Shanghai Inst Intelligent Sci & Technol, Shanghai 201804, Peoples R China
[4] Tongji Univ, Inst Carbon Neutral, Coll Environm Sci & Engn, Shanghai 200092, Peoples R China
[5] Univ Sydney, Sch Elect & Informat Engn, Fac Engn, Sydney, NSW 2006, Australia
基金
美国国家科学基金会;
关键词
Relays; Games; Optimization; Cooperative communication; Costs; Channel capacity; Signal to noise ratio; power control; multi-agent reinforcement learning; Stackelberg game; DETERMINISTIC POLICY GRADIENT; RELAY SELECTION; ALLOCATION; POWER; OPTIMIZATION;
D O I
10.1109/TCCN.2024.3400516
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
This paper aims to balance performance and cost in a two-hop wireless cooperative communication network where the source and relays have contradictory optimization goals and make decisions in a distributed manner. This differs from most existing works that have typically assumed that source and relay nodes follow a schedule created implicitly by a central controller. We propose that the relays form an alliance in an attempt to maximize the benefit of relaying while the source aims to increase the channel capacity cost-effectively. To this end, we establish the trade problem as a Stackelberg game, and prove the existence of its equilibrium. Another important aspect is that we use multi-agent reinforcement learning (MARL) to approach the equilibrium in a situation where the instantaneous channel state information (CSI) is unavailable, and the source and relays do not have knowledge of each other's goal. A multi-agent deep deterministic policy gradient-based framework is designed, where the relay alliance and the source act as agents. Experiments demonstrate that the proposed method can obtain an acceptable performance that is close to the game-theoretic equilibrium for all players under time-invariant environments, which considerably outperforms its potential alternatives and is only about 2.9% away from the optimal solution.
引用
收藏
页码:2193 / 2208
页数:16
相关论文
共 50 条
  • [31] Levels of Realism for Cooperative Multi-agent Reinforcement Learning
    Cunningham, Bryan
    Cao, Yong
    ADVANCES IN SWARM INTELLIGENCE, ICSI 2012, PT I, 2012, 7331 : 573 - 582
  • [32] Cooperative Multi-agent Reinforcement Learning for Inventory Management
    Khirwar, Madhav
    Gurumoorthy, Karthik S.
    Jain, Ankit Ajit
    Manchenahally, Shantala
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES: APPLIED DATA SCIENCE AND DEMO TRACK, ECML PKDD 2023, PT VI, 2023, 14174 : 619 - 634
  • [33] The Cooperative Reinforcement Learning in a Multi-Agent Design System
    Liu, Hong
    Wang, Jihua
    PROCEEDINGS OF THE 2013 IEEE 17TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN (CSCWD), 2013, : 139 - 144
  • [34] Cooperative Multi-Agent Reinforcement Learning in Express System
    Li, Yexin
    Zheng, Yu
    Yang, Qiang
    CIKM '20: PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, 2020, : 805 - 814
  • [35] A review of cooperative multi-agent deep reinforcement learning
    Afshin Oroojlooy
    Davood Hajinezhad
    Applied Intelligence, 2023, 53 : 13677 - 13722
  • [36] A review of cooperative multi-agent deep reinforcement learning
    Oroojlooy, Afshin
    Hajinezhad, Davood
    APPLIED INTELLIGENCE, 2023, 53 (11) : 13677 - 13722
  • [37] Centralized reinforcement learning for multi-agent cooperative environments
    Chengxuan Lu
    Qihao Bao
    Shaojie Xia
    Chongxiao Qu
    Evolutionary Intelligence, 2024, 17 : 267 - 273
  • [38] Centralized reinforcement learning for multi-agent cooperative environments
    Lu, Chengxuan
    Bao, Qihao
    Xia, Shaojie
    Qu, Chongxiao
    EVOLUTIONARY INTELLIGENCE, 2024, 17 (01) : 267 - 273
  • [39] Training Cooperative Agents for Multi-Agent Reinforcement Learning
    Bhalla, Sushrut
    Subramanian, Sriram G.
    Crowley, Mark
    AAMAS '19: PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS, 2019, : 1826 - 1828
  • [40] Cooperative Exploration for Multi-Agent Deep Reinforcement Learning
    Liu, Iou-Jen
    Jain, Unnat
    Yeh, Raymond A.
    Schwing, Alexander G.
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139