居住分类下的长期教育投资政策学习
Learning Long-Term Educational Investment Policies under Residential Sorting
浏览论文内容
中文总结 AI 辅助
该研究针对居住分类下公立教育投资分配的公平与效率问题，构建动态多智能体框架，用强化学习得出的政策在模拟中实现了良好的入学机会与公平性平衡，减少了教育领域的社会经济分层。
中文摘要 AI 辅助
当入学机会取决于居住情况时，有效且公平地分配公立学校投资是一项难题。学校改善会提高周边住房需求与价格，重塑入学情况，还可能限制低收入家庭的入学机会。这些影响会随着居住分类改变学校的构成、质量及未来投资需求而演变。现有方法通常单独研究学校资金、家庭选择和住房市场，而静态模型会忽略它们相互关联的长期影响。我们通过一个动态多智能体框架解决这一缺口，该框架关联了政府投资、家庭分类、住房价格、人口流动、入学情况及不断变化的学校质量。政府规划者使用强化学习（RL）来确定多年分配政策，这些政策在考虑家庭反应的同时，平衡总体教育入学机会与公平性。在模拟中，我们基于RL的政策在代表性基准中达到了最高的入学机会水平（0.4780）和第二低的入学机会基尼系数（0.0164），展现出良好的有效性与公平性平衡。结果还表明教育入学的社会经济分层有所减少。通过明确教育-住房的反馈，我们的框架支持对学校投资如何随时间塑造教育机会进行长期分析。
英文摘要
Allocating public-school investment effectively and fairly is difficult when school access depends on residence. School improvements can raise nearby housing demand and prices, reshape enrollment, and potentially limit access for lower-income households. These effects evolve as residential sorting changes school composition, quality, and future investment needs. Existing approaches often study school funding, household choice, and housing markets separately, while static models can miss their interconnected, long-term effects. We address this gap with a dynamic multi-agent framework that links government investment, household sorting, housing prices, population turnover, enrollment, and evolving school quality. A government planner uses reinforcement learning (RL) to identify multiyear allocation policies that account for household responses while balancing aggregate educational access and equity. In simulations, our RL-based policy attains the highest access level (0.4780) and second-lowest access Gini coefficient (0.0164) among representative baselines, demonstrating a favorable effectiveness-equity balance. The results also indicate reduced socioeconomic stratification in educational access. By making education-housing feedback explicit, our framework supports long-term analysis of how school investment shapes educational opportunity over time.
