arXiv：cs.LG· Yefei Zhang, Yuxuan Zhao·· 3 小时前
多智能体学习如何在公共物品困境中形成空间格局
Spatial Pattern Formation from Multi-Agent Learning in Public Goods Dilemmas
AI 导读
研究发现，固定数量的合作者与背叛者用表格 Q-learning 和局部观察独立学习移动策略时，合作者学习会在资源峰值周围形成集群，其与背叛者的共同适应会改变集群强度和移动方式。在固定训练预算下，合作者高学习率、背叛者低学习率时福利损失最大，部分条件下还会出现由共同方向偏好支撑的行进带。测试条件下，合作者学习使平均集体福利低于随机移动，而让智能体为其造成的拥挤付费可恢复大部分福利损失。
正文
Abstract:Spatial public goods models show that prescribed movement toward richer locations can generate spatial patterns. We ask how such patterns emerge when agents learn where to move and how learning rates shape their consequences for collective welfare. Fixed populations of cooperators and defectors independently learn movement policies using tabular Q-learning and local observations. Cooperator learning generates clusters around resource peaks, while co-adaptation changes their strength and motion. At a fixed training budget, the largest welfare losses occur when cooperators learn at high rates and defectors at low rates. In part of this regime, learned policies also generate traveling bands supported by a shared directional preference. The conditions supporting travel change with further training, so these patterns reflect training history rather than an established asymptotic outcome. Across the tested learning-rate conditions with cooperator learning, mean collective welfare falls below random movement because increased crowding outweighs gains in resource benefit. Charging agents for the crowding they impose on others during learning recovers much of the welfare loss in the tested conditions. These results connect learning rates to the emergence and welfare costs of spatial organization driven by individual rewards.
| Subjects: | Multiagent Systems (cs.MA); Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.12321 [cs.MA] |
| (or arXiv:2610.12321v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12321 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yefei Zhang [view email]
[v1]
Thu, 8 Oct 2026 17:03:35 UTC (847 KB)
来源：arXiv：cs.LG · arxiv.org