Strategic Coordination for Evolving Multi-agent Systems: A Hierarchical Reinforcement and Collective Learning Approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qin, Chuhao, Pournaras, Evangelos
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909799911784448
author Qin, Chuhao
Pournaras, Evangelos
author_facet Qin, Chuhao
Pournaras, Evangelos
contents Decentralized combinatorial optimization in evolving multi-agent systems poses significant challenges, requiring agents to balance long-term decision-making, short-term optimized collective outcomes, while preserving autonomy of interactive agents under unanticipated changes. Reinforcement learning offers a way to model sequential decision-making through dynamic programming to anticipate future environmental changes. However, applying multi-agent reinforcement learning (MARL) to decentralized combinatorial optimization problems remains an open challenge due to the exponential growth of the joint state-action space, high communication overhead, and privacy concerns in centralized training. To address these limitations, this paper proposes Hierarchical Reinforcement and Collective Learning (HRCL), a novel approach that leverages both MARL and decentralized collective learning based on a hierarchical framework. Agents take high-level strategies using MARL to group possible plans for action space reduction and constrain the agent behavior for Pareto optimality. Meanwhile, the low-level collective learning layer ensures efficient and decentralized coordinated decisions among agents with minimal communication. Extensive experiments in a synthetic scenario and real-world smart city application models, including energy self-management and drone swarm sensing, demonstrate that HRCL significantly improves performance, scalability, and adaptability compared to the standalone MARL and collective learning approaches, achieving a win-win synthesis solution.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18088
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Strategic Coordination for Evolving Multi-agent Systems: A Hierarchical Reinforcement and Collective Learning Approach
Qin, Chuhao
Pournaras, Evangelos
Multiagent Systems
Machine Learning
Decentralized combinatorial optimization in evolving multi-agent systems poses significant challenges, requiring agents to balance long-term decision-making, short-term optimized collective outcomes, while preserving autonomy of interactive agents under unanticipated changes. Reinforcement learning offers a way to model sequential decision-making through dynamic programming to anticipate future environmental changes. However, applying multi-agent reinforcement learning (MARL) to decentralized combinatorial optimization problems remains an open challenge due to the exponential growth of the joint state-action space, high communication overhead, and privacy concerns in centralized training. To address these limitations, this paper proposes Hierarchical Reinforcement and Collective Learning (HRCL), a novel approach that leverages both MARL and decentralized collective learning based on a hierarchical framework. Agents take high-level strategies using MARL to group possible plans for action space reduction and constrain the agent behavior for Pareto optimality. Meanwhile, the low-level collective learning layer ensures efficient and decentralized coordinated decisions among agents with minimal communication. Extensive experiments in a synthetic scenario and real-world smart city application models, including energy self-management and drone swarm sensing, demonstrate that HRCL significantly improves performance, scalability, and adaptability compared to the standalone MARL and collective learning approaches, achieving a win-win synthesis solution.
title Strategic Coordination for Evolving Multi-agent Systems: A Hierarchical Reinforcement and Collective Learning Approach
topic Multiagent Systems
Machine Learning
url https://arxiv.org/abs/2509.18088