Embodiment-Induced Coordination Regimes in Tabular Multi-Agent Q-Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-agent Reinforcement LearningRepresentation LearningSimilar Papers 제목 키워드 기반
Multi-Agent Debate: A Unified Agentic Framework for Tabular Anomaly Detection
Tabular anomaly detection is often handled by single detectors or static ensembles, even though strong performance on tabular data typically comes from heterogeneous model families (e.g., tree ensembles, deep tabular net…
Anomaly DetectionEmergent Coordination and Phase Structure in Independent Multi-Agent Reinforcement Learning
A clearer understanding of when coordination emerges, fluctuates, or collapses in decentralized multi-agent reinforcement learning (MARL) is increasingly sought in order to characterize the dynamics of multi-agent learni…
Multi-agent Reinforcement LearningRoboOS-NeXT: A Unified Memory-based Framework for Lifelong, Scalable, and Robust Multi-Robot Collaboration
The proliferation of collaborative robots across diverse tasks and embodiments presents a central challenge: achieving lifelong adaptability, scalable coordination, and robust scheduling in multi-agent systems. Existing …
ICLAD: In-Context Learning for Unified Tabular Anomaly Detection Across Supervision Regimes
Anomaly detection on tabular data is commonly studied under three supervision regimes, including one-class settings that assume access to anomaly-free training samples, fully unsupervised settings with unlabeled and pote…
Anomaly DetectionHybrid Human-Agent Social Dilemmas in Energy Markets
In hybrid populations where humans delegate strategic decision-making to autonomous agents, understanding when and how cooperative behaviors can emerge remains a key challenge. We study this problem in the context of ene…
Reinforcement Learning