Multi-task coalition parallel formation strategy based on reinforcement learning

被引：0

作者：

Department of Computer and Information Science, Hefei University of Technology, Hefei 230009, China ^{[1
]}

不详 ^{[2
]}

机构：

[1] Department of Computer and Information Science, Hefei University of Technology

[2] Engineering Research Center of Safety Critical Industrial Measurement and Control Technology

来源：

Zidonghua Xuebao | 2008年 / 3卷 / 349-352期

基金：

中国国家自然科学基金; 高等学校博士学科点专项科研基金;

关键词：

Markov decision process; Multi-task coalition; Parallel formation; Reinforcement learning;

D O I：

10.3724/SP.J.1004.2008.00349

中图分类号：

学科分类号：

摘要：

Agent coalition is an important manner of agents' coordination and cooperation. Forming a coalition, agents can enhance their ability to solve problems and obtain more utilities. In this paper, a novel multi-task coalition parallel formation strategy is presented, and the conclusion that the process of multi-task coalition formation is a Markov decision process is testified theoretically. Moreover, reinforcement learning is used to solve agents' behavior strategy, and the process of multi-task coalition parallel formation is described. In multi-task oriented domains, the strategy can effectively and parallel form multi-task coalitions.

引用

页码：349 / 352

页数：3

共 50 条

[31] UCP: a unified framework for code generation with pseudocode-based multi-task learning and reinforcement alignment [J].

Wen, Yongjun ;

Cui, Zhihao ;

Liu, Yihao ;

Zhang, Zhao ;

Zhou, Jiake ;

Tang, Lijun .

JOURNAL OF SUPERCOMPUTING, 2025, 81 (08)

[32] A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline [J].

Zhao, Yingying ;

Dong, Mingzhi ;

Wang, Yujiang ;

Feng, Da ;

Lv, Qin ;

Dick, Robert P. ;

Li, Dongsheng ;

Lu, Tun ;

Gu, Ning ;

Shang, Li .

IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 24 :2150-2163

[33] Multi-task lane-free driving strategy for Connected and Automated Vehicles: A multi-agent deep reinforcement learning approach [J].

Berahman, Mehran ;

Karalakou, Athanasia ;

Rostami-Shahrbabaki, Majid ;

Bogenberger, Klaus .

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2025, 154

[34] Multi-Task Reinforcement Learning in Reproducing Kernel Hilbert Spaces via Cross-Learning [J].

Cervino, Juan ;

Bazerque, Juan Andres ;

Calvo-Fullana, Miguel ;

Ribeiro, Alejandro .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2021, 69 :5947-5962

[35] Dynamic Split Computing Framework for Multi-Task Learning Models: A Deep Reinforcement Learning Approach [J].

Ko, Haneul ;

Seo, Sangwon ;

Pack, Sangheon .

IEEE ACCESS, 2025, 13 :103439-103450

[36] Personalized Federated Hypernetworks for Multi-Task Reinforcement Learning in Microgrid Energy Demand Response [J].

Jang, Doseok ;

Spangher, Lucas ;

Srivastava, Tarang ;

Yan, Larry ;

Spanos, Costas J. .

PROCEEDINGS OF THE 10TH ACM INTERNATIONAL CONFERENCE ON SYSTEMS FOR ENERGY-EFFICIENT BUILDINGS, CITIES, AND TRANSPORTATION, BUILDSYS 2023, 2023, :79-88

[37] Reinforcement Learning Driving Strategy based on Auxiliary Task for Multi-Scenarios Autonomous Driving [J].

Sun, Jingbo ;

Fang, Xing ;

Zhang, Qichao .

2023 IEEE 12TH DATA DRIVEN CONTROL AND LEARNING SYSTEMS CONFERENCE, DDCLS, 2023, :1337-1342

[38] Decentralized multi-task reinforcement learning policy gradient method with momentum over networks [J].

Shi Junru ;

Wang Qiong ;

Liu Muhua ;

Ji Zhihang ;

Zheng Ruijuan ;

Wu Qingtao .

Applied Intelligence, 2023, 53 :10365-10379

[39] Decentralized multi-task reinforcement learning policy gradient method with momentum over networks [J].

Shi Junru ;

Wang Qiong ;

Liu Muhua ;

Ji Zhihang ;

Zheng Ruijuan ;

Wu Qingtao .

APPLIED INTELLIGENCE, 2023, 53 (09) :10365-10379

[40] xMTF: A Formula-Free Model for Reinforcement-Learning-Based Multi-Task Fusion in Recommender Systems [J].

Cao, Yang ;

Zhang, Changhao ;

Chen, Xiaoshuang ;

Zhan, Kaiqiao ;

Wang, Ben .

PROCEEDINGS OF THE ACM WEB CONFERENCE 2025, WWW 2025, 2025, :3840-3849

← 1 2 3 4 5 →