High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Qinyu, Zhu, Yuanyang, Wu, Xuefei, Chen, Chunlin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917036130566144
author Xu, Qinyu
Zhu, Yuanyang
Wu, Xuefei
Chen, Chunlin
author_facet Xu, Qinyu
Zhu, Yuanyang
Wu, Xuefei
Chen, Chunlin
contents The ability to model interactions among agents is crucial for effective coordination and understanding their cooperation mechanisms in multi-agent reinforcement learning (MARL). However, previous efforts to model high-order interactions have been primarily hindered by the combinatorial explosion or the opaque nature of their black-box network structures. In this paper, we propose a novel value decomposition framework, called Continued Fraction Q-Learning (QCoFr), which can flexibly capture arbitrary-order agent interactions with only linear complexity $\mathcal{O}\left({n}\right)$ in the number of agents, thus avoiding the combinatorial explosion when modeling rich cooperation. Furthermore, we introduce the variational information bottleneck to extract latent information for estimating credits. This latent information helps agents filter out noisy interactions, thereby significantly enhancing both cooperation and interpretability. Extensive experiments demonstrate that QCoFr not only consistently achieves better performance but also provides interpretability that aligns with our theoretical analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20218
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning
Xu, Qinyu
Zhu, Yuanyang
Wu, Xuefei
Chen, Chunlin
Multiagent Systems
Artificial Intelligence
The ability to model interactions among agents is crucial for effective coordination and understanding their cooperation mechanisms in multi-agent reinforcement learning (MARL). However, previous efforts to model high-order interactions have been primarily hindered by the combinatorial explosion or the opaque nature of their black-box network structures. In this paper, we propose a novel value decomposition framework, called Continued Fraction Q-Learning (QCoFr), which can flexibly capture arbitrary-order agent interactions with only linear complexity $\mathcal{O}\left({n}\right)$ in the number of agents, thus avoiding the combinatorial explosion when modeling rich cooperation. Furthermore, we introduce the variational information bottleneck to extract latent information for estimating credits. This latent information helps agents filter out noisy interactions, thereby significantly enhancing both cooperation and interpretability. Extensive experiments demonstrate that QCoFr not only consistently achieves better performance but also provides interpretability that aligns with our theoretical analysis.
title High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning
topic Multiagent Systems
Artificial Intelligence
url https://arxiv.org/abs/2510.20218