mlsanityData to 14 Oct 2026

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

arXiv 2506.18651 ↗First posted 23 Jun 2025cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 38 references that are in the map. First posted on arXiv 23 Jun 2025.

Builds on

26 of 38 references.

References · 26

  1. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 752
  2. 2017Population Based Training of Neural Networkscited by 367
  3. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 313
  4. 2020Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?cited by 294
  5. 2013The Complexity of Decentralized Control of Markov Decision Processescited by 231
  6. 2019MAVEN: Multi-Agent Variational Explorationcited by 185
  7. 2019Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Controlcited by 164
  8. 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 137
  9. 2017Emergent Complexity via Multi-Agent Competitioncited by 120
  10. 2021Celebrating Diversity in Shared Multi-Agent Reinforcement Learningcited by 98
  11. 2019Influence-Based Multi-Agent Explorationcited by 75
  12. 2019Multi-Agent Actor-Critic with Hierarchical Graph Attention Networkcited by 33
14 more
  1. 2021Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learningcited by 18
  2. 2022Transferring Multi-Agent Reinforcement Learning Policies for Autonomous Driving using Sim-to-Realcited by 17
  3. 2023System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learningcited by 14
  4. 2024Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Taskscited by 13
  5. 2024Controlling Behavioral Diversity in Multi-Agent Reinforcement Learningcited by 11
  6. 2023PIMbot: Policy and Incentive Manipulation for Multi-Robot Reinforcement Learning in Social Dilemmascited by 6
  7. 2024Bi-CL: A Reinforcement Learning Framework for Robots Coordination Through Bi-level Optimizationcited by 4
  8. 2023Decentralized Multi-Agent Reinforcement Learning with Global State Predictioncited by 3
  9. 2024MA4DIV: Multi-Agent Reinforcement Learning for Search Result Diversificationcited by 2
  10. 2021Collective Iterative Learning Control: Exploiting Diversity in Multi-Agent Systems for Reference Tracking Taskscited by 1
  11. 2022Safe adaptation in multiagent competitioncited by 1
  12. 2024Agent-Agnostic Centralized Training for Decentralized Multi-Agent Cooperative Drivingcited by 1
  13. 2024Intrinsic Action Tendency Consistency for Cooperative Multi-Agent Reinforcement Learningcited by 1
  14. 2024HARP: Human-Assisted Regrouping with Permutation Invariant Critic for Multi-Agent Reinforcement Learningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Optimizing Team Behavior via Extremum-seeking Control in Multi-agent Reinforcement Learning
  2. 2024The impact of behavioral diversity in multi-agent reinforcement learning
  3. 2025Constructive Conflict-Driven Multi-Agent Reinforcement Learning for Strategic Diversity
  4. 2026Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning
  5. 2026PopGen: Generating Semantically Diverse Populations for Zero-Shot Coordination
  6. 2024Measuring Policy Distance for Multi-Agent Reinforcement Learning
  7. 2026Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
  8. 2026Rethinking Policy Diversity in Ensemble Policy Gradient in Large-Scale Reinforcement Learning