Hierarchical Reinforcement Learning For Optimal Agent Grouping In Cooperative Systems

Abstract

This paper presents a hierarchical reinforcement learning (RL) approach to address the agent grouping or pairing problem in cooperative multi-agent systems. The goal is to simultaneously learn the optimal grouping and agent policy. By employing a hierarchical RL framework, we distinguish between high-level decisions of grouping and low-level agents' actions. Our approach utilizes the CTDE (Centralized Training with Decentralized Execution) paradigm, ensuring efficient learning and scalable execution. We incorporate permutation-invariant neural networks to handle the homogeneity and cooperation among agents, enabling effective coordination. The option-critic algorithm is adapted to manage the hierarchical decision-making process, allowing for dynamic and optimal policy adjustments.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhu2025hierarchical

Related papers

• Hierarchical Reinforcement Learning With Opponent Modeling For Distributed Multi-agent Cooperation (2022)5.84
• Strategic Coordination For Evolving Multi-agent Systems: A Hierarchical Reinforcement And Collective Learning Approach (2025)0.00
• HAVEN: Hierarchical Cooperative Multi-agent Reinforcement Learning With Dual Coordination Mechanism (2021)0.00
• Subgoal-based Hierarchical Reinforcement Learning For Multi-agent Collaboration (2024)0.00
• Developing Cooperative Policies For Multi-stage Reinforcement Learning Tasks (2022)0.00
• Scalable Centralized Deep Multi-agent Reinforcement Learning Via Policy Gradients (2018)0.00
• Fully Decentralized Cooperative Multi-agent Reinforcement Learning: A Survey (2024)0.00
• Optimization For Reinforcement Learning: From Single Agent To Cooperative Agents (2019)14.62