Embodiment-Induced Coordination Regimes in Tabular Multi-Agent Q-Learning

TL;DR

This study critically evaluates the effectiveness of centralized versus independent Q-learning in multi-agent systems under embodiment constraints, revealing that centralized methods do not always enhance coordination and can sometimes hinder it.

Contribution

It provides a controlled, tabular analysis showing that embodiment constraints influence the relative performance of centralized and independent multi-agent Q-learning, challenging common assumptions.

Findings

Centralized learning often outperforms independent learning but not consistently.

Embodiment constraints can turn coordination into a liability.

Role asymmetry affects the stability of coordination regimes.

Abstract

Centralized value learning is often assumed to improve coordination and stability in multi-agent reinforcement learning, yet this assumption is rarely tested under controlled conditions. We directly evaluate it in a fully tabular predator-prey gridworld by comparing independent and centralized Q-learning under explicit embodiment constraints on agent speed and stamina. Across multiple kinematic regimes and asymmetric agent roles, centralized learning fails to provide a consistent advantage and is frequently outperformed by fully independent learning, even under full observability and exact value estimation. Moreover, asymmetric centralized-independent configurations induce persistent coordination breakdowns rather than transient learning instability. By eliminating confounding effects from function approximation and representation learning, our tabular analysis isolates coordination structure as the primary driver of these effects. The results show that increased coordination can become a liability under embodiment constraints, and that the effectiveness of centralized learning is fundamentally regime and role dependent rather than universal.