Heterogeneity in Multi-Agent Reinforcement Learning

Heterogeneity is a fundamental property in multi-agent reinforcement learning (MARL), which is closely related not only to the functional differences of agents, but also to policy diversity and environmentalinteractions. However, theMARLfieldcurrentlylacksa rigorousdefinitionanddeeperunderstandingofheterogeneity. This paper systematically discusses heterogeneity in MARL from the perspectives of definition, quantification, and utilization. First, based on an agent-level modeling of MARL, we categorize heterogeneity into five types and provide mathematical definitions. Second, we define the concept of heterogeneity distance and propose a practical quantification method. Third, we design a heterogeneity-based multi-agent dynamic parameter sharing algorithm as an example of the application of our methodology. Case studies demonstrate that our method can effectively identify and quantify various types of agent heterogeneity. Experimental results show that the proposed algorithm, compared to other parameter sharing baselines, has better interpretability and stronger adaptability. The proposed methodology will help the MARL community gain a more comprehensive and profound understanding of heterogeneity, and further promote the development of practical algorithms. 1

Authors

• Tianyi Hu National Key Laboratory of Cognition and Decision Intelligence for Complex Systems, CASIA & School of Artificial Intelligence, UCAS
• Zhiqiang Pu National Key Laboratory of Cognition and Decision Intelligence for Complex Systems, CASIA & School of Artificial Intelligence, UCAS
• Yuan Wang National Key Laboratory of Cognition and Decision Intelligence for Complex Systems, CASIA & School of Artificial Intelligence, UCAS
• Tenghai Qiu National Key Laboratory of Cognition and Decision Intelligence for Complex Systems, CASIA
• Min Chen School of Computer Science and Engineering, South China University of Technology
• Xin Yu National Key Laboratory of Cognition and Decision Intelligence for Complex Systems, CASIA

Keywords

• Multi-Agent Reinforcement Learning
• Heterogeneity