Structured Diversity Control: A Dual-Level Framework for Group-Aware Multi-Agent Coordination

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Shuocun, Hu, Huawen, Liu, Xuan, Yao, Yincheng, Shi, Enze, Zhang, Shu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914362515521536
author Yang, Shuocun
Hu, Huawen
Liu, Xuan
Yao, Yincheng
Shi, Enze
Zhang, Shu
author_facet Yang, Shuocun
Hu, Huawen
Liu, Xuan
Yao, Yincheng
Shi, Enze
Zhang, Shu
contents Controlling the behavioral diversity is a pivotal challenge in multi-agent reinforcement learning (MARL), particularly in complex collaborative scenarios. While existing methods attempt to regulate behavioral diversity by directly differentiating across all agents, they lack deep characterization and learning of multi-agent composition structures. This limitation leads to suboptimal performance or coordination failures when facing more complex or challenging tasks. To bridge this gap, we introduce Structured Diversity Control (SDC), a framework that redefines the system-wide diversity metric as a weighted combination of intra-group diversity, which is minimized for cohesion and inter-group diversity, which is maximized for specialization. The trade-off is governed by a pre-set Diversity Structure Factor (DSF), allowing for fine-grained, group-aware control over the collective strategy. Our method directly constrains the policy architecture without altering reward functions. This structural definition of diversity enables SDC to deliver substantial performance gains across various experiments, including increasing average rewards by up to 47.1\% in multi-target pursuit and reducing episode lengths by 12.82\% in complex neutralization scenarios. The proposed method offers a novel analytical perspective on the problem of cooperation in group-aware multi-agent systems.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18651
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Structured Diversity Control: A Dual-Level Framework for Group-Aware Multi-Agent Coordination
Yang, Shuocun
Hu, Huawen
Liu, Xuan
Yao, Yincheng
Shi, Enze
Zhang, Shu
Artificial Intelligence
Controlling the behavioral diversity is a pivotal challenge in multi-agent reinforcement learning (MARL), particularly in complex collaborative scenarios. While existing methods attempt to regulate behavioral diversity by directly differentiating across all agents, they lack deep characterization and learning of multi-agent composition structures. This limitation leads to suboptimal performance or coordination failures when facing more complex or challenging tasks. To bridge this gap, we introduce Structured Diversity Control (SDC), a framework that redefines the system-wide diversity metric as a weighted combination of intra-group diversity, which is minimized for cohesion and inter-group diversity, which is maximized for specialization. The trade-off is governed by a pre-set Diversity Structure Factor (DSF), allowing for fine-grained, group-aware control over the collective strategy. Our method directly constrains the policy architecture without altering reward functions. This structural definition of diversity enables SDC to deliver substantial performance gains across various experiments, including increasing average rewards by up to 47.1\% in multi-target pursuit and reducing episode lengths by 12.82\% in complex neutralization scenarios. The proposed method offers a novel analytical perspective on the problem of cooperation in group-aware multi-agent systems.
title Structured Diversity Control: A Dual-Level Framework for Group-Aware Multi-Agent Coordination
topic Artificial Intelligence
url https://arxiv.org/abs/2506.18651