竞争可自发催生学习者群体的分工，无需额外激励。
Emergent Specialization in Learner Populations: Competition as the Source of Diversity
- 通过竞争排斥与生态位偏好追踪实现自发分化。
- 平均专业化指数达0.75，效果量超过20。
- 适合多智能体协作与动态环境下的自适应系统。
在没有显式通信或多样性激励的情况下，学习者群体如何发展出协调且多样的行为？我们证明，仅靠竞争就足以引发涌现式专业化——学习者通过竞争动态自发分为不同环境下的专业个体，符合生态位理论。我们提出NichePopulation算法，结合竞争排斥与生态位亲和力追踪。在六种真实场景（加密货币交易、商品价格、天气预报、太阳辐射、城市交通、空气质量）中验证，平均专业化指数为0.75，效应量（Cohen's d）大于20。关键发现：(1) 当λ=0（无生态位奖励）时，学习者仍达到SI > 0.30，证明专业化为真正涌现；(2) 多样性群体相比同质基线提升26.5%，体现方法级分工优势；(3) 相比MARL基线（QMIX, MAPPO, IQL）性能提升4.3倍，速度加快4倍。
原文摘要 · Abstract (English)
How can populations of learners develop coordinated, diverse behaviors without explicit communication or diversity incentives? We demonstrate that competition alone is sufficient to induce emergent specialization -- learners spontaneously partition into specialists for different environmental regimes through competitive dynamics, consistent with ecological niche theory. We introduce the NichePopulation algorithm, a simple mechanism combining competitive exclusion with niche affinity tracking. Validated across six real-world domains (cryptocurrency trading, commodity prices, weather forecasting, solar irradiance, urban traffic, and air quality), our approach achieves a mean Specialization Index of 0.75 with effect sizes of Cohen's d > 20. Key findings: (1) At lambda=0 (no niche bonus), learners still achieve SI > 0.30, proving specialization is genuinely emergent; (2) Diverse populations outperform homogeneous baselines by +26.5% through method-level division of labor; (3) Our approach outperforms MARL baselines (QMIX, MAPPO, IQL) by 4.3x while being 4x faster.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。