Graph-Based Complexity Metrics for Multi-Agent Curriculum Learning: A Validated Approach to Task Ordering in Cooperative Coordination Environments

TL;DR

This paper introduces a graph-based complexity metric for multi-agent curriculum learning that accurately predicts task difficulty and improves training efficiency in cooperative environments.

Contribution

It develops and empirically validates a novel complexity metric based on agent dependency, interference, and goal overlap for guiding multi-agent curriculum learning.

Findings

Strong correlation (rho=0.952) between predicted complexity and empirical difficulty

Achieved 56x performance improvement in tight coordination tasks

Demonstrated systematic task progression in cooperative navigation

Abstract

Multi-agent reinforcement learning (MARL) faces significant challenges in task sequencing and curriculum design, particularly for cooperative coordination scenarios. While curriculum learning has demonstrated success in single-agent domains, principled approaches for multi-agent coordination remain limited due to the absence of validated task complexity metrics. This approach presents a graph-based coordination complexity metric that integrates agent dependency entropy, spatial interference patterns, and goal overlap analysis to predict task difficulty in multi-agent environments. The complexity metric achieves strong empirical validation with rho = 0.952 correlation (p < 0.001) between predicted complexity and empirical difficulty determined by random agent performance evaluation. This approach evaluates the curriculum learning framework using MADDPG across two distinct coordination environments: achieving 56x performance improvement in tight coordination tasks (MultiWalker) and demonstrating systematic task progression in cooperative navigation (Simple Spread). Through systematic analysis, coordination tightness emerges as a predictor of curriculum learning effectiveness, where environments requiring strict agent interdependence benefit substantially from structured progression. This approach provides a validated complexity metric for multi-agent curriculum design and establishes empirical guidelines for multi-robot coordination applications.