机器学习辅助的基于智能体模型校准：基于代理的优化结合遗传算法与粒子群优化
Machine learning-assisted calibration of Agent-based Models: surrogate-based optimization with Genetic Algorithm and Particle Swarm Optimization
浏览论文内容
中文总结 AI 辅助
本研究提出将机器学习代理嵌入遗传算法和粒子群优化中，以校准基于智能体模型，通过筛选候选解减少模拟成本，实验表明在两种模型上显著提升精度并节省时间，且最佳配置随模型复杂度变化。
中文摘要 AI 辅助
校准基于智能体模型（ABM）是困难的，因为其目标景观是随机且崎岖的，且只能通过昂贵的黑盒模拟进行评估。本研究通过将机器学习代理嵌入遗传算法（GA）和粒子群优化（PSO）中，将内环代理辅助进化计算（SAEC）适配于ABM校准。在每次迭代中，代理筛选候选解，而模拟器仅验证前50%的候选，从而减少模拟需求同时纠正代理误差。我们在两个对比鲜明的ABM——Brock-Hommes资产定价模型和岛屿生长模型上，评估了由两种优化器、五种代理和四个校准目标组合而成的48种全因子配置。参数恢复通过伪真值进行测量。相对于最强的纯优化器基线，最佳的机器学习辅助配置在Brock-Hommes上降低了RMSE 20.0%，在岛屿模型上降低了63.8%，同时分别减少了32.1%和61.1%的计算时间。ANOVA与Dunnett事后检验确认，在Brock-Hommes的两种优化器下以及岛屿模型上的GA下，每种代理均显著节省时间。在岛屿模型上，没有代理在参数恢复准确性上与纯优化器基线有显著差异；因此，报告的准确性提升是最佳配置的结果，而非在此样本量下解析出的平均效应。最佳的代理-优化器-目标组合随ABM复杂度而变化，表明代理辅助校准依赖于模型，不存在通用的默认配方。
英文摘要
Calibrating an agent-based model (ABM) is difficult because its objective landscape is stochastic and rugged, and can be evaluated only through costly black-box simulations. This study adapts inner-loop surrogate-assisted evolutionary computation (SAEC) to ABM calibration by embedding a machine-learning surrogate within genetic algorithm (GA) and particle swarm optimisation (PSO). At each iteration, the surrogate screens the candidates and the simulator validates only the top 50%, reducing simulation demand while correcting surrogate errors. We evaluate a full factorial of 48 configurations combining two optimisers, five surrogates, and four calibration objectives on two contrasting ABMs, the Brock-Hommes asset-pricing model and the Island growth model. Parameter recovery is measured against pseudo-true values. Relative to the strongest pure-optimiser baseline, the best ML-assisted configurations reduce RMSE by 20.0% on Brock-Hommes and 63.8% on Island, while reducing computation time by 32.1% and 61.1%, respectively. ANOVA with Dunnett's post-hoc tests confirms significant time savings for every surrogate under both Brock-Hommes optimisers and under GA on Island. No surrogate differs significantly from the pure-optimiser baseline in parameter-recovery accuracy on Island; the reported accuracy gains are therefore best-configuration outcomes rather than average effects resolved at this sample size. The best surrogate-optimiser-objective combination changes with ABM complexity, indicating that surrogate-assisted calibration depends on the model and does not admit a universal default recipe.
发表机构
- Pukyong National University（釜庆国立大学）
机构由 AI 辅助整理，请以论文原文为准。
