Building predictive agent models based on the inclusion of machine learning models in determining the state of agents

The field of agent modeling continues to evolve towards the creation of more intelligent agents. This raises the conceptual problem of finding a balance between the determinism of agents' behavior and the ability of these agents to learn and predict their condition. One of the potential ways to solve this problem is to consider the possibility of developing an intermediate approach in the creation of agents, in which agents maintain the determinism of their behavior, but at the same time are able to predict their condition and correct behavior. The article presents a new approach to building intelligent agents, which combines the classical approach of building agents based on a priori set rules and the application of machine learning methods in the rules of agent behavior. A mathematical description of the proposed function for calculating the state of an agent using machine learning models is presented, as well as an algorithm for calculating the states of agents in the model. An example of building an agent model using the proposed approach is also given. The proposed approach makes it possible to develop agent models of complex systems in which agents are reactive but are able to predict their state and take into account the predict in determining their current state.

1. Macal C., North M. Introductory tutorial: Agent-based modeling and simulation. In: Proceedings of the Winter Simulation Conference 2014, 7–10 December 2014, Savannah, USA. IEEE; 2014. pp. 6–20. https://doi.org/10.1109/WSC.2014.7019874

2. Kuznetsov A.V. The short review of multi-agent models. Large-Scale Systems Control. 2018;(71):6–44. (In Russ.).

3. Mehdizadeh M., Nordfjaern T., Klöckner C.A. A systematic review of the agent-based modelling/simulation paradigm in mobility transition. Technological Forecasting and Social Change. 2022;184. https://doi.org/10.1016/j.techfore.2022.122011

4. Ale Ebrahim Dehkordi M., Lechner J., Ghorbani A., Nikolic I., Chappin É., 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. 2023;26(1). https://doi.org/10.18564/jasss.5016

5. Lorscheid I. Learning Agents for Human Complex Systems. In: 2014 IEEE 38th International Computer Software and Applications Conference Workshops, 21–25 July 2014, Vasteras, Sweden. IEEE; 2014. pp. 432–437. https://doi.org/10.1109/COMPSACW.2014.73

6. Bashardoust A., Safaei D., Haki K., Shrestha Y.R. Employing Machine Learning to Advance Agent-based Modeling in Information Systems Research. In: Forty-Fourth International Conference on Information Systems, ICIS 2023, 10–13 December 2023, Hyderabad, India. URL: https://aisel.aisnet.org/icis2023/adv_theory/adv_theory/3/

7. 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;123. https://doi.org/10.1016/j.simpat.2022.102707

8. Brearcliffe D.K., Crooks A. Creating Intelligent Agents: Combining Agent-Based Modeling with Machine Learning. In: Proceedings of the 2020 Conference of The Computational Social Science Society of the Americas, 8–11 October 2020, Online. Cham: Springer; 2021. pp. 31–58. https://doi.org/10.1007/978-3-030-83418-0_3

9. Kavak H., Padilla J.J., Lynch C.J., Diallo S.Y. Big data, agents, and machine learning: towards a data-driven agent-based modeling approach. In: ANSS '18: Proceedings of the Annual Simulation Symposium: SpringSim '18: 2018 Spring Simulation Multiconference, 15–18 April 2018, Baltimore, USA. San Diego: Society for Computer Simulation International; 2018. pp. 1–12. https://dl.acm.org/doi/10.5555/3213032.3213044

10. Ramchandani P., Paich M., Rao A. Incorporating Learning into Decision Making in Agent Based Models. In: Progress in Artificial Intelligence: 18th EPIA Conference on Artificial Intelligence, EPIA 2017, 5–8 September 2017, Porto, Portugal. Cham: Springer; 2017. pp. 789–800. https://doi.org/10.1007/978-3-319-65340-2_64

11. Adenuga O.T., Mpofu K., Kanisuru A.M. Agent-based Control System: A Review and Platform for Reconfigurable Bending Press Machine. Procedia Manufacturing. 2019;35:50–55. https://doi.org/10.1016/j.promfg.2019.05.007

12. Lisovenko A.S., Limanovskaya O.V. Modelirovanie sostoyaniya vozdushnoi linii elektroperedachi na osnove ucheta defektnosti provodov i uslovii okruzhayushchei sredy. In: Fizika. Tekhnologii. Innovatsii: Sbornik statei VIII Mezhdunarodnoi molodezhnoi nauchnoi konferentsii, 17–21 May 2021, Yekaterinburg, Russia. Yekaterinburg: Ural Federal University; 2021. pp. 157–168. (In Russ.).

13. Lisovenko A.S., Limanovskaya O.V., Gavrilov I.V., Meshchaninov V.N. Agent-based system for predicting the patient's condition in personalized gerontology. In: Imitatsionnoe modelirovanie: teoriya i praktika (IMMOD-2023): Sbornik trudov odinnadtsatoi vserossiiskoi nauchno-prakticheskoi konferentsii po imitatsionnomu modelirovaniyu i ego primeneniyu v nauke i promyshlennosti, 18–20 October 2023, Kazan, Russia. Kazan: Izdatel'stvo AN RT; 2023. pp. 121–129. (In Russ.).

14. Shishmareva A.S., Bimbas E.S., Limanovskaya O.V. Predicting early orthodontic treatment results and development of the dentofacial system without orthodontic treatment in 3-12-year-old children. Pediatric dentistry and dental prophylaxis. 2023;23(3):243–254. (In Russ.). https://doi.org/10.33925/1683-3031-2023-660