Assisted-Value Factorization with Latent Interaction in Cooperate Multi-Agent Reinforcement Learning

Zhitong Zhao, Ya Zhang (), Siying Wang, Yang Zhou, Ruoning Zhang and Wenyu Chen
Additional contact information
Zhitong Zhao: College of Management Science, Chengdu University of Technology, Chengdu 610059, China
Ya Zhang: College of Management Science, Chengdu University of Technology, Chengdu 610059, China
Siying Wang: School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
Yang Zhou: School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
Ruoning Zhang: School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
Wenyu Chen: School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China

Mathematics, 2025, vol. 13, issue 9, 1-21

Abstract: With the development of value decomposition methods, multi-agent reinforcement learning (MARL) has made significant progress in balancing autonomous decision making with collective cooperation. However, the collaborative dynamics among agents are continuously changing. The current value decomposition methods struggle to adeptly handle these dynamic changes, thereby impairing the effectiveness of cooperative policies. In this paper, we introduce the concept of latent interaction, upon which an innovative method for generating weights is developed. The proposed method derives weights from the history information, thereby enhancing the accuracy of value estimations. Building upon this, we further propose a dynamic masking mechanism that recalibrates history information in response to the activity level of agents, improving the precision of latent interaction assessments. Experimental results demonstrate the improved training speed and superior performance of the proposed method in both a multi-agent particle environment and the StarCraft Multi-Agent Challenge.

Keywords: reinforcement learning; decentralized partially observable Markov decision process (Dec-POMDP); multi-agent reinforcement learning; multi-agent value decomposition (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/9/1429/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/9/1429/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:9:p:1429-:d:1643513

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().