Work

DDWCN: A Dual-Stream Dynamic Strategy Modeling Network for Multi-Agent Elastic Collaboration

Year: 2025

Type: article

Abstract: In the domain of multi-agent reinforcement learning, conventional algorithms such as VDN, QMIX, and QTRAN have exhibited favorable performance in static task scenarios. However, these algorithms encounter challenges due to their limited capacity to model elastic collaboration scenarios, wherein the number of agents and the state-action space undergo dynamic changes over time. To address this limitation, this paper proposes a novel multi-agent collaboration mechanism: the Dual-Stream Dynamic Weight Compensation Network (DDWCN). This method employs a dual-stream action modeling network for the classification and processing of actions. It integrates an information compensation network and a dynamic weight fusion network. These additions have been demonstrated to enhance the network’s robustness and generalization capabilities for complex collaborative tasks. Extensive experimentation on a variety of benchmark tasks in StarCraft II has validated the effectiveness of DDWCN. The findings indicate that this approach exhibits commendable scalability and reliability in authentic multi-agent collaboration scenarios, underscoring its extensive applicability.

Source: Applied Sciences

DOI: 10.3390/app15169164

Authors: Zhenduo Meng, Xitai Na, Tuo Wang, Jinglong Liu, Wenda Wang

Institution: Inner Mongolia University

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,896

Funder: Inner Mongolia University