GHQ: Grouped Hybrid Q Learning For Heterogeneous Cooperative Multi-agent Reinforcement Learning

Abstract

Previous deep multi-agent reinforcement learning (MARL) algorithms have achieved impressive results, typically in homogeneous scenarios. However, heterogeneous scenarios are also very common and usually harder to solve. In this paper, we mainly discuss cooperative heterogeneous MARL problems in Starcraft Multi-Agent Challenges (SMAC) environment. We firstly define and describe the heterogeneous problems in SMAC. In order to comprehensively reveal and study the problem, we make new maps added to the original SMAC maps. We find that baseline algorithms fail to perform well in those heterogeneous maps. To address this issue, we propose the Grouped Individual-Global-Max Consistency (GIGM) and a novel MARL algorithm, Grouped Hybrid Q Learning (GHQ). GHQ separates agents into several groups and keeps individual parameters for each group, along with a novel hybrid structure for factorization. To enhance coordination between groups, we maximize the Inter-group Mutual Information (IGMI) between

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keyyu2023ghq

Related papers

• Maximum Entropy Heterogeneous-agent Reinforcement Learning (2023)0.00
• Heterogeneous-agent Reinforcement Learning (2023)0.00
• Self-clustering Hierarchical Multi-agent Reinforcement Learning With Extensible Cooperation Graph (2024)2.26
• Heterogeneous Multi-agent Reinforcement Learning For Zero-shot Scalable Collaboration (2024)6.34
• End-to-end Optimization Of Llm-driven Multi-agent Search Systems Via Heterogeneous-group-based Reinforcement Learning (2025)0.00
• Learning Heterogeneous Agent Cooperation Via Multiagent League Training (2022)7.16
• Heterogeneous Multi-robot Reinforcement Learning (2023)6.77
• Cooperative Multi-agent Reinforcement Learning With Hypergraph Convolution (2021)5.84