MAAIDec 7, 2023

Mastering Complex Coordination through Attention-based Dynamic Graph

arXiv:2312.04245v1h-index: 11ICONIP
Originality Incremental advance
AI Analysis

This addresses coordination challenges in multi-agent systems for applications like robotics or gaming, though it appears incremental as it builds on existing graph-based methods.

The paper tackles the problem of high computational cost and performance decline in large-scale multi-agent coordination by introducing DAGMIX, a dynamic graph-based value factorization method that uses attention mechanisms, which significantly outperforms previous state-of-the-art methods in large-scale scenarios.

The coordination between agents in multi-agent systems has become a popular topic in many fields. To catch the inner relationship between agents, the graph structure is combined with existing methods and improves the results. But in large-scale tasks with numerous agents, an overly complex graph would lead to a boost in computational cost and a decline in performance. Here we present DAGMIX, a novel graph-based value factorization method. Instead of a complete graph, DAGMIX generates a dynamic graph at each time step during training, on which it realizes a more interpretable and effective combining process through the attention mechanism. Experiments show that DAGMIX significantly outperforms previous SOTA methods in large-scale scenarios, as well as achieving promising results on other tasks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes