ПРИМЕНЕНИЕ МЕТОДОВ МАШИННОГО ОБУЧЕНИЯ В АГЕНТНОМ МОДЕЛИРОВАНИИ
DOI:
https://doi.org/10.5281/zenodo.12667180Ключевые слова:
агентное моделирование, машинное обучение, графовые нейронные сети, нейронные сети, метод опорных векторов, случайный лес, градиентный бустинг, k ближайших соседей, гауссовский процесс, деревья принятия решений.Аннотация
Агентное моделирование является мощным инструментом для изучения сложных систем, позволяя анализировать поведение агентов и их взаимодействие на микроуровне. Особую актуальность их применение получает в случаях недостаточных и/или некачественных открытых статистических данных. В статье рассмотрены подходы к классификации методов и примеры их применения для создания агентных моделей, способствующих пониманию и прогнозированию экономических процессов. Представлена систематизация применения современных методов машинного обучения и их элементов для решения отдельных задач по моделированию пространственных взаимосвязей. Рассмотрено, какие роли и функции выполняют алгоритмы машинного обучения на различных этапах разработки агентных моделей, а также приведены примеры их использования в агентном моделировании экономических процессов и выявлен потенциал подобного подхода для улучшения прогностической и объясняющей способности этих моделей. Области применения машинного обучения условно разделены на 4 блока: предварительная обработка данных (которая включает в себя удаление выбросов, заполнение пропусков и нормализацию данных), формирование поведения агентов (в том числе с разной степенью рациональности и обучаемости), построение суррогатных моделей (полностью заменяющих собой исходную модель с целью снижения трудо-, времязатрат и требований к вычислительным мощностям) и постобработка данных (которая включает кластеризацию, разработку форм визуализации и очистку данных). Такие методы, как деревья решений и байесовские сети, играют ключевую роль в извлечении правил из данных и формировании поведенческих стратегий агентов. Работа подчеркивает важность учета шумов и аномалий в данных, а также необходимость адаптации моделей к реальным условиям. По результатам проведенного обзора сформированы рекомендации по применению отдельных методов в зависимости от особенностей моделирования. Результаты исследования имеют практическое значение для разработки более точных и эффективных агентных моделей в различных областях, таких как экономика, экология и социальные науки.
Скачивания
Библиографические ссылки
1. Alexandridis K., Pijanowski B.C. Assessing multiagent parcelization performance in the MABEL simulation model using Monte Carlo replication experiments // Environment and Planning B: Planning and Design, Vol. 34, No. 2, 2007. pp. 223-244.
2. Lei Z., Pijanowski B.C., Alexandridis K.T., Olson J. Distributed modeling architecture of a multi-Agent-Based behavioral economic landscape (MABEL) model // Simulation, Vol. 81, No. 7, 2005. pp. 503-515.
3. Sun Z., Müller D. A framework for modeling payments for ecosystem services with agent-based models, Bayesian belief networks and opinion dynamics models // Environmental Modelling & Software. 2013. No. 45. pp. 15–28.
4. Laite R., Portman N., Sankaranarayanan K. Behavioral analysis of agent based service channel design using neural networks, 2016.
5. Chu T.Q., Drogoul A., Boucher A., and Zucker J.D. Interactive learning of independent experts’ criteria for rescue simulations // Journal of Universal Computer Science, Vol. 15, No. 13, 2009. pp. 2719-2743.
6. Turgut Y., Bozdag C.E. A framework proposal for machine learning-driven agent-based models through a case study analysis // Simulation Modelling Practice and Theory. 2023. Т. 123.
7. Taghikhah F., Voinov A., Filatova T., and Polhill J.G. Machine-assisted agent-based modeling: Opening the black box // Journal of Computational Science, No. 64, 2022.
8. Dehkordi M., Lechner J., Ghorbani A., Nikolic I., Chappin E., and Herder P. Using Machine Learning for Agent Specifications in Agent-Based Models and Simulations: A Critical Review and Guidelines // Journal of Artificial Societies and Social Simulation, Vol. 1, No. 26, Sep 2023.
9. Heppenstall A.J., Crooks A.T., See, L.M., Batty, M. Agent-based models of geographical systems // Springer Science & Business Media, 2011.
10. Zhang H., Vorobeychik Y., Letchford J., Lakkaraju K. Data-driven agent-based modeling, with application to rooftop solar adoption // Autonomous Agents and Multi-Agent Systems, Vol. 30, 2016. pp. 1023-1049.
11. Lamperti F., Roventini A., and Sani A. Agent-based model calibration using machine learning surrogates // Journal of Economic Dynamics and Control, Vol. 90, 2018. pp. 366-389.
12. Gaube V., Kaiser C., Wildenberg M., Adensam H., Fleissner P., Kobler J., Lutz J., Schaumberger A., Schaumberger J., Smetschka B. Combining agent-based and stock-flow modelling approaches in a participative analysis of the integrated land systemin Reichraming // Austria. Landscape Ecology, Vol. 9, No. 24, 2009. pp. 1149–1165.
13. Abdulkareem S., Augustijn E.W., Mustafa Y., and Filatova T. Intelligent judgements over health risks in a spatial agent-based model // International Journal of Health Geographics, Vol. 1, No. 17, Aug 2018.
14. Кузнецов М. Графовые нейронные сети : учебник по машинному обучению. 2024. – URL: https://education.yandex.ru/handbook/ml/article/grafovye-nejronnye-seti (дата обращения: 04.04.2024).
15. Sengupta R., Chapman C., Sarkar D., and Bortolamiol S. Automated extraction of movement rationales for building agent-based models: Example of a Red Colobus Monkey group. In L. Perez, E.K. Kim & R. Sengupta (Eds.), Agent-Based in the Age of Complexity Science Models and Geospatial Big Data, Berlin Heidelberg: Springer, 2018. pp. 59–71.
16. Rosés R., Kadar C., and Malleson N. A data-driven agent-based simulation to predict crime patterns in an urban environment // Computers, Environment and Urban Systems, Vol. 89, No. 101660, 2021.
17. Sánchez-Maroño N., Alonso-Betanzos A., Fontenla-Romero O., Polhill J.G., and Craig T. Empirically-derived behavioral rules in agent-based models using decision trees learned from questionnaire data // Agent-Based Modeling of Sustainable Behaviors. 2017. pp. 53-76.
18. Kocabas V., Dragicevic S. Bayesian networks and agent-based modeling approach for urban land-use and population density change: A BNAS model // Journal of Geographical Systems. 2013. Vol. 4. No. 15. pp. 403–426.
19. Tian F., Li M., Han X., Liu H., and Mo B. A production-living-ecological space model for land-use optimisation: A case study of the core Tumen River region in China // Ecological Modelling. 2020. Vol. 437. No. 109310.
20. Pooyandeh M., Marceau D. Incorporating Bayesian learning in agent-based simulation of stakeholders’ negotiation // Computers, Environment and Urban Systems, No. 48, 2014. pp. 73–85.
21. Ma L., Arentze T., Borgers A., and Timmermans H. Modelling land-use decisions under conditions of uncertainty // Computers, Environment and Urban Systems. 2007. Vol. 4. No. 31. pp. 461–476.
22. Axtell R.L., Farmer J.D. Agent-Based Modeling in Economics and Finance: Past, Present, and Future // Journal of Economic Literature.
23. Gehrke J.D., Wojtusiak J. Traffic Prediction for Agent Route Planning // Computational Science – ICCS 2008. Germany. – 2008. – Т. 5103. – С. 692-701.
24. Rand W. Machine Learning Meets Agent-Based Modeling: When not to go to a Bar // Conference on Social Agents: Results and Prospects. 2006.
25. Osoba O.A., Vardavas R., Grana J., Zutshi R., Jaycocks A. Policy-focused Agent-based Modeling using RL Behavioral Models // 19th IEEE International Conference On Machine Learning And Applications. USA. 2020.
26. Mu T., Zheng S., Trott A.R. Modeling Bounded Rationality in Multi-Agent Simulations Using Rationally Inattentive Reinforcement Learning // Transactions on Machine Learning Research. – 2022. – Т. 12. – С. 1-12.
27. Dahlke J., Bogner K., Mueller M., Berger T., Pyka A., Ebersberger B. Is the Juice Worth the Squeeze? Machine Learning (ML) In and For Agent-Based Modelling (ABM) // arXiv. 2020. – URL: https://doi.org/10.48550/arXiv.2003.11985.
28. Shapley L.S. Stochastic games // Proceedings of the national academy of sciences. – 1953. – Т. 39. – № 10. – С. 1095-1100.
29. Shoham Y., Powers R., Grenager T. If multi-agent learning is the answer, what is the question? // Artificial Intelligence. – 2007. – Т. 171. – № 7. – С. 365-377.
30. Fiosins M., Fiosina J., Müller J., Görmer J. Reconciling Strategic and Tactical Decision Making in Agent-Oriented Simulation of Vehicles in Urban Traffic // Proceedings of the 4th International ICST Conference on Simulation Tools and Techniques. Spain. 2012.
31. Littman M.L. Markov games as a framework for multi-agent reinforcement learning // Machine Learning Proceedings. USA. – 1994. – С. 157-163.
32. Kleinberg J., Ludwig J., Mullainathan S., Obermeyer Z. Prediction Policy Problems // American Economic Review. – 2015. – Т. 105. – № 5. – С. 491-495.
33. Geman S., Bienenstock E., Doursat R. Neural Networks and the Bias/Variance Dilemma // Neural Computation. – 1992. – Т. 4. – № 1. – С. 1-58.
34. Llacay B., Peffer G. Categorical surrogation of agent-based models: A comparativestudy of machine learning classifiers // Expert Systems. 2022. pp. 1-40.
35. Angione C., Silverman E., Yaneske E. Using Machine Learning to Emulate Agent-Based Simulations // arXiv, 2021.
36. Chen B., Li W., and Pei H. IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC) // Deep Recurrent Q-Learning for Research on Complex Economic System. Chongqing, China. 2020. pp. 583–588.
37. Xie S., Lawniczak A. & Gan C. Optimal number of clusters in explainable data analysis of agent-based simulation experiments // Journal of Computational Science. 2022. Vol. 62.
38. Luo Y., Chai C., Qin X., Tang N. & Li G. Interactive cleaning for progressive visualization through composite questions // Proceedings of the IEEE International Conference on Data Engineering. 2020.
39. Wang Y., Feng K., Chu X., Zhang J., Fu C.W., Sedlmair M., Yu X., & Chen B. A perception-driven approach to supervised dimensionality reduction for visualization // IEEE Transactions on Visualization and Computer Graphics. 2017. Vol. 24. No. 5. pp. 1828–1840.
40. Luo Y., Qin X., Tang & Li. Deepeye: towards automatic data visualization // Proceedings of the IEEE International Conference on Data Engineering. 2018. pp. 101–112.
41. Hu K., Bakker M.A., Li S., Kraska T. & Hidalgo C. VizML: A machine learning approach to visualization recommendation // Proceedings of the ACM Conference on Human Factors in Computing Systems. 2019.
42. Chen C., Wang C., Bai X., Zhang P. & Li C. Generativemap: Visualization and exploration of dynamic density maps via generative learning model // IEEE Transactions on Visualization and Computer Graphics. 2019. Vol. 26. No. 1. pp. 216–226.
43. Han J., Wang C. TSR-TVD: Temporal super-resolution for time-varying data analysis and visualization // IEEE Transactions on Visualization and Computer Graphics. 2019. Vol. 1. No. 26. pp. 216–226.
44. Berger M., Li J. & Levine J.A. A generative model for volume rendering // IEEE Transactions on Visualization and Computer Graphics. 2019. Vol. 4. No. 25. pp. 1636–1650.
45. He W., Wang J., Guo H., Wang K.C., Shen H.W., Raj M., Nashed Y.S. & Peterka T. InSituNet: Deep image synthesis for parameter space exploration of ensemble simulations // IEEE Transactions on Visualization and Computer Graphics. 2019. Vol. 1. No. 26. pp. 23–33.
References
1. Alexandridis K., Pijanowski B.C. (2007) Assessing multiagent parcelization performance in the MABEL simulation model using Monte Carlo replication experiments. Environment and Planning B: Planning and Design. Vol. 34, No. 2. pp. 223-244. (In English).
2. Lei Z., Pijanowski B.C., Alexandridis K.T., Olson J. (2005) Distributed modeling architecture of a multi-Agent-Based behavioral economic landscape (MABEL) model. Simulation. Vol. 81, No. 7. pp. 503-515. (In English).
3. Sun Z., Müller D. (2013) A framework for modeling payments for ecosystem services with agent-based models, Bayesian belief networks and opinion dynamics models. Environmental Modelling & Software. No. 45. pp. 15–28. (In English).
4. Laite R., Portman N., Sankaranarayanan K. (2016) Behavioral analysis of agent based service channel design using neural networks. (In English).
5. Chu T.Q., Drogoul A., Boucher A., and Zucker J.D. (2009) Interactive learning of independent experts’ criteria for rescue simulations. Journal of Universal Computer Science. Vol. 15, No. 13. pp. 2719-2743. (In English).
6. Turgut Y., Bozdag C.E. (2023) A framework proposal for machine learning-driven agent-based models through a case study analysis. Simulation Modelling Practice and Theory. 123. (In English).
7. Taghikhah F., Voinov A., Filatova T., & Polhill J.G. (2022) Machine-assisted agent-based modeling: Opening the black box. Journal of Computational Science. No. 64. (In English).
8. Dehkordi M., Lechner J., Ghorbani A., Nikolic I., Chappin E., & Herder P. (2023) Using Machine Learning for Agent Specifications in Agent-Based Models and Simulations: A Critical Review and Guidelines. Journal of Artificial Societies and Social Simulation. Vol. 1, No. 26, Sep 2023. (In English).
9. Heppenstall A.J., Crooks A.T., See, L.M., Batty, M. (2011) Agent-based models of geographical systems. Springer Science & Business Media. (In English).
10. Zhang H., Vorobeychik Y., Letchford J., Lakkaraju K. (2016) Data-driven agent-based modeling, with application to rooftop solar adoption. Autonomous Agents and Multi-Agent Systems. Vol. 30. pp. 1023-1049. (In English).
11. Lamperti F., Roventini A., & Sani A. (2018) Agent-based model calibration using machine learning surrogates. Journal of Economic Dynamics and Control. Vol. 90. pp. 366-389. (In English).
12. Gaube V., Kaiser C., Wildenberg M., Adensam H., Fleissner P., Kobler J., Lutz J., Schaumberger A., Schaumberger J., Smetschka B. (2009) Combining agent-based and stock-flow modelling approaches in a participative analysis of the integrated land systemin Reichraming. Austria. Landscape Ecology. Vol. 9, No. 24. pp. 1149–1165. (In English).
13. Abdulkareem S., Augustijn E.W., Mustafa Y., & Filatova T. (2018) Intelligent judgements over health risks in a spatial agent-based model. International Journal of Health Geographics. Vol. 1, No. 17, Aug 2018. (In English).
14. Kuznetsov M. (2024) Graph neural networks : a textbook on machine learning. URL: https://education.yandex.ru/handbook/ml/article/grafovye-nejronnye-seti (date of application: 04.04.2024). (In Russian).
15. Sengupta R., Chapman C., Sarkar D., & Bortolamiol S. (2018) Automated extraction of movement rationales for building agent-based models: Example of a Red Colobus Monkey group. In L. Perez, E.K. Kim & R. Sengupta (Eds.), Agent-Based in the Age of Complexity Science Models and Geospatial Big Data, Berlin Heidelberg: Springer. pp. 59–71. (In English).
16. Rosés R., Kadar C., & Malleson N. (2021) A data-driven agent-based simulation to predict crime patterns in an urban environment. Computers, Environment and Urban Systems. Vol. 89, No. 101660. (In English).
17. Sánchez-Maroño N., Alonso-Betanzos A., Fontenla-Romero O., Polhill J.G., & Craig T. (2017) Empirically-derived behavioral rules in agent-based models using decision trees learned from questionnaire data. Agent-Based Modeling of Sustainable Behaviors. pp. 53-76. (In English).
18. Kocabas V., Dragicevic S. (2013) Bayesian networks and agent-based modeling approach for urban land-use and population density change: A BNAS model. Journal of Geographical Systems. Vol. 4. No. 15. pp. 403–426. (In English).
19. Tian F., Li M., Han X., Liu H., & Mo B. (2020) A production-living-ecological space model for land-use optimisation: A case study of the core Tumen River region in China. Ecological Modelling. Vol. 437. No. 109310. (In English).
20. Pooyandeh M., Marceau D. (2014) Incorporating Bayesian learning in agent-based simulation of stakeholders’ negotiation. Computers, Environment and Urban Systems. No. 48. pp. 73–85. (In English).
21. Ma L., Arentze T., Borgers A., & Timmermans H. (2007) Modelling land-use decisions under conditions of uncertainty. Computers, Environment and Urban Systems. Vol. 4. No. 31. pp. 461–476. (In English).
22. Axtell R.L., Farmer J.D. Agent-Based Modeling in Economics and Finance: Past, Present, and Future. Journal of Economic Literature. (In English).
23. Gehrke J.D., Wojtusiak J. (2008) Traffic Prediction for Agent Route Planning. Computational Science – ICCS 2008. Germany. Vol. 5103. pp. 692-701. (In English).
24. Rand W. (2006) Machine Learning Meets Agent-Based Modeling: When not to go to a Bar. Conference on Social Agents: Results and Prospects. (In English).
25. Osoba O.A., Vardavas R., Grana J., Zutshi R., Jaycocks A. (2020) Policy-focused Agent-based Modeling using RL Behavioral Models. 19th IEEE International Conference On Machine Learning And Applications, 2020, USA. (In English).
26. Mu T., Zheng S., Trott A.R. (2022) Modeling Bounded Rationality in Multi-Agent Simulations Using Rationally Inattentive Reinforcement Learning. Transactions on Machine Learning Research. Vol. 12. pp. 1-12. (In English).
27. Dahlke J., Bogner K., Mueller M., Berger T., Pyka A., Ebersberger B. (2020) Is the Juice Worth the Squeeze? Machine Learning (ML) In and For Agent-Based Modelling (ABM). arXiv. URL: https://doi.org/10.48550/arXiv.2003.11985. (In English).
28. Shapley L.S. (1953) Stochastic games. Proceedings of the national academy of sciences. Vol. 39. No. 10. Pp. 1095-1100. (In English).
29. Shoham Y., Powers R., Grenager T. (2007) If multi-agent learning is the answer, what is the question? Artificial Intelligence. Vol. 171. No. 7. pp. 365-377. (In English).
30. Fiosins M., Fiosina J., Müller J., Görmer J. (2012) Reconciling Strategic and Tactical Decision Making in Agent-Oriented Simulation of Vehicles in Urban Traffic. Proceedings of the 4th International ICST Conference on Simulation Tools and Techniques, Spain, 2012. (In English).
31. Littman M.L. (1994) Markov games as a framework for multi-agent reinforcement learning. Machine Learning Proceedings, USA, 1994. pp. 157-163. (In English).
32. Kleinberg J., Ludwig J., Mullainathan S., Obermeyer Z. (2015) Prediction Policy Problems. American Economic Review. Vol. 105. No. 5. pp. 491-495. (In English).
33. Geman S., Bienenstock E., Doursat R. (1992) Neural Networks and the Bias/Variance Dilemma. Neural Computation. Vol. 4. No. 1. pp. 1-58. (In English).
34. Llacay B., Peffer G. (2022) Categorical surrogation of agent-based models: A comparativestudy of machine learning classifiers. Expert Systems. pp. 1-40. (In English).
35. Angione C., Silverman E., Yaneske E. (2021) Using Machine Learning to Emulate Agent-Based Simulations. arXiv. (In English).
36. Chen B., Li W., and Pei H. (2020) Deep Recurrent Q-Learning for Research on Complex Economic System. IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC). Chongqing, China. 2020. pp. 583–588. (In English).
37. Xie S., Lawniczak A. & Gan C. (2022) Optimal number of clusters in explainable data analysis of agent-based simulation experiments. Journal of Computational Science. Vol. 62. (In English).
38. Luo Y., Chai C., Qin X., Tang N. & Li G. (2020) Interactive cleaning for progressive visualization through composite questions. Proceedings of the IEEE International Conference on Data Engineering. 2020. (In English).
39. Wang Y., Feng K., Chu X., Zhang J., Fu C.W., Sedlmair M., Yu X., & Chen B. (2017) A perception-driven approach to supervised dimensionality reduction for visualization. IEEE Transactions on Visualization and Computer Graphics. Vol. 24. No. 5. pp. 1828–1840. (In English).
40. Luo Y., Qin X., Tang & Li. (2018) Deepeye: towards automatic data visualization. Proceedings of the IEEE International Conference on Data Engineering. 2018. pp. 101–112. (In English).
41. Hu K., Bakker M.A., Li S., Kraska T. & Hidalgo C. (2019) VizML: A machine learning approach to visualization recommendation. Proceedings of the ACM Conference on Human Factors in Computing Systems. 2019. (In English).
42. Chen C., Wang C., Bai X., Zhang P. & Li C. (2019) Generativemap: Visualization and exploration of dynamic density maps via generative learning model. IEEE Transactions on Visualization and Computer Graphics. Vol. 26. No. 1. pp. 216–226. (In English).
43. Han J., Wang C. (2019) TSR-TVD: Temporal super-resolution for time-varying data analysis and visualization. IEEE Transactions on Visualization and Computer Graphics. Vol. 1. No. 26. pp. 216–226. (In English).
44. Berger M., Li J. & Levine J.A. (2019) A generative model for volume rendering. IEEE Transactions on Visualization and Computer Graphics.Vol. 4. No. 25. pp. 1636–1650. (In English).
45. He W., Wang J., Guo H., Wang K.C., Shen H.W., Raj M., Nashed Y.S. & Peterka T. (2019) InSituNet: Deep image synthesis for parameter space exploration of ensemble simulations. IEEE Transactions on Visualization and Computer Graphics. Vol. 1. No. 26. pp. 23–33. (In English).
Загрузки
Опубликован
Выпуск
Раздел
Лицензия
Это произведение доступно по лицензии Creative Commons «Attribution-NonCommercial» («Атрибуция — Некоммерческое использование») 4.0 Всемирная.
Статьи журнала «Новое в экономической кибернетике» находятся в открытом доступе и распространяются в соответствии с условиями Лицензионного Договора с Донецким Государственным университетом, который бесплатно предоставляет авторам неограниченное распространение и самостоятельное архивирование.
