Pokémon GO Team Optimization: A Comparative Study of Classic Metaheuristic Algorithms

Gabriel Bueno Guimarães; Rodrigo Colnago Contreras; Arthur Costa Gorgonio; Anne Magály de Paula Canuto

doi:10.5753/jis.2026.6773

Authors

Gabriel Bueno Guimarães Independent Researcher https://orcid.org/0009-0007-4271-4051
Rodrigo Colnago Contreras Federal University of São Paulo https://orcid.org/0000-0003-4003-7791
Arthur Costa Gorgonio Federal University of Rio Grande do Norte https://orcid.org/0000-0002-1824-9600
Anne Magály de Paula Canuto Federal University of Rio Grande do Norte https://orcid.org/0000-0002-3684-3814

DOI:

https://doi.org/10.5753/jis.2026.6773

Keywords:

Metaheuristic Algorithms, Team Composition Optimization, Pokémon GO, Combinatorial Optimization, Game Analytics

Abstract

Pokémon GO team selection can be formulated as a combinatorial optimization problem in which the goal is to generate a three-Pokémon counter-team that maximizes performance against a given rival team under simulated battles. In this study, we establish and evaluate a compact set of classical metaheuristic baselines for this task, namely Simulated Annealing (SA), Tabu Search (TS), Variable Neighborhood Search (VNS), Genetic Algorithm (GA), Ant Colony Optimization (ACO), and Cuckoo Search (CS), using a fixed benchmark of 1,000 rival teams adopted from [da Silva Oliveira et al., 2020]. All methods are assessed under the same dataset, fitness function, and simulator, and we report solution quality (fitness) and elapsed time over repeated runs. The results reveal distinct quality and cost regimes among the evaluated baselines. VNS achieves the highest mean fitness under the adopted stopping conditions, whereas the SA variants provide the lowest runtimes with competitive fitness. We further analyze convergence behavior on the hardest rival teams and characterize the local-search effort of VNS, providing evidence on stabilization patterns and per-iteration workload. These findings deliver reproducible optimization baselines and convergence evidence for Pokémon GO team generation, supporting method selection under different computational budgets and providing reference points for future work on faster convergence and hybrid search strategies.

Downloads

Download data is not yet available.

References

Alhijawi, B. and Awajan, A. (2024). Genetic algorithms: Theory, genetic operators, solutions, and applications. Evolutionary Intelligence, 17(3):1245–1256. DOI: https://doi.org/10.1007/s12065-023-00822-6.

Almufti, S. (2025). Metaheuristics algorithms: Overview, applications, and modifications. Deep Science Publishing India. https://doi.org/10.70593/978-93-7185-454-2.

Balbinot, R. A., Costa, L. M., Souza, A. C. C., and Souza, F. C. M. (2024). Developing competitive strategies for legends of runeterra using genetic algorithm. In Simpósio Brasileiro de Jogos e Entretenimento Digital (SBGames), pages 513–531. SBC. DOI: https://doi.org/10.5753/sbgames.2024.241320.

Barros, P. and Sciutti, A. (2022). All by myself: Learning individualized competitive behavior with a contrastive reinforcement learning optimization. Neural Networks, 150:364–376. DOI: https://doi.org/10.1016/j.neunet.2022.03.013.

Costa, L. M., Souza, A. C. C., and Souza, F. C. M. (2019). An approach for team composition in league of legends using genetic algorithm. In 2019 18th Brazilian Symposium on Computer Games and Digital Entertainment (SBGames), pages 52–61. IEEE. DOI: https://doi.org/10.1109/sbgames.2019.00018.

da Silva Oliveira, S., Silva, G. E. P. L., Gorgônio, A. C., Barreto, C. A., Canuto, A. M., and Carvalho, B. M. (2020). Team recommendation for the pokémon go game using optimization approaches. In 2020 19th Brazilian Symposium on Computer Games and Digital Entertainment (SBGames), pages 163–170. IEEE. DOI: https://doi.org/10.1109/sbgames51465.2020.00030.

Delahaye, D., Chaimatanan, S., and Mongeau, M. (2018). Simulated annealing: From basics to applications. In Handbook of metaheuristics, pages 1–35. Springer. DOI: https://doi.org/10.1007/978-3-319-91086-4_1.

Dorigo, M., Maniezzo, V., and Colorni, A. (1996). Ant system: optimization by a colony of cooperating agents. IEEE transactions on systems, man, and cybernetics, part b (cybernetics), 26(1):29–41. DOI: https://doi.org/10.1109/3477.484436.

García-Sánchez, P., Tonda, A., Squillero, G., Mora, A., and Merelo, J. J. (2016). Evolutionary deckbuilding in hearthstone. In 2016 IEEE Conference on Computational Intelligence and Games (CIG), pages 1–8. IEEE. DOI: https://doi.org/10.1109/cig.2016.7860426.

Gen, M. and Lin, L. (2023). Genetic algorithms and their applications. In Springer handbook of engineering statistics, pages 635–674. Springer. DOI: https://doi.org/10.1007/978-1-4471-7503-2_33.

Gomes, A. (2009). Uma introdução à busca tabu. Technical report, Instituto de Matemática e Estatística, Universidade de São Paulo.

Hansen, P., Mladenović, N., Brimberg, J., and Pérez, J. A. M. (2019). Variable neighborhood search. Springer.

Harris, M. D. (2016). Pokémon go post-evolution cp: A model. Quantitative Archaeology blog.

Haumann, T. and Höppner, F. (2025). Adaptivity of card recommendation systems for legends of code and magic. IEEE Transactions on Games. DOI: https://doi.org/10.1109/cog60054.2024.10645596.

Khare, S., Callejo, S., and Espinoza, M. (2023). Pokemon team predictions: Which characteristics of a pokemon give the best winning rate and can they be used for prediction? Graduate-level course project, Florida State University, not peer-reviewed.

Kora, P. and Yadlapalli, P. (2017). Crossover operators in genetic algorithms: A review. International Journal of Computer Applications, 162(10). DOI: https://doi.org/10.5120/ijca2017913370.

Mladenović, N. and Hansen, P. (1997). Variable neighborhood search. Computers & operations research, 24(11):1097–1100. DOI: https://doi.org/10.1016/s0305-0548(97)00031-2.

Niantic, Inc. (2016). Pokémon go. [link]. Acesso em: 22 mar. 2026.

Pokémon GO Wiki (2024). Combat power. [link]. Accessed: 25 March 2026.

PwC (2023). Perspectives and insights: Global entertainment and media outlook 2023–2027. [link], Acesso em: 22 mar. 2026.

Reis, S., Novais, R., Reis, L. P., and Lau, N. (2023a). An adversarial approach for automated pokémon team building and meta-game balance. IEEE Transactions on Games. DOI: https://doi.org/10.1109/tg.2023.3273157.

Reis, S., Novais, R., Reis, L. P., and Lau, N. (2023b). An adversarial approach for automated pokémon team building and metagame balance. IEEE Transactions on Games, 16(2):365–375. DOI: https://doi.org/10.1109/tg.2023.3273157.

Reis, S., Reis, L. P., and Lau, N. (2021). Vgc ai competition-a new model of meta-game balance ai competition. In 2021 IEEE Conference on Games (CoG), pages 01–08. IEEE. DOI: https://doi.org/10.1109/cog52621.2021.9618985.

Sarantinos, N. R. (2022). Teamwork under extreme uncertainty: Ai for pokemon ranks 33rd in the world. arXiv preprint arXiv:2212.13338. DOI: https://doi.org/10.48550/arXiv.2212.13338.

Van Laarhoven, P. J., Aarts, E. H., van Laarhoven, P. J., and Aarts, E. H. (1987). Simulated annealing. Springer.

Yang, X.-S. and Deb, S. (2009). Cuckoo search via lévy flights. In 2009 World congress on nature & biologically inspired computing (NaBIC), pages 210–214. Ieee. DOI: https://doi.org/10.1109/nabic.2009.5393690.

Yang, Y.-J., Yeh, T.-S., and Chiang, T.-C. (2021). Deck building in collectible card games using genetic algorithms: A case study of legends of code and magic. In 2021 IEEE Symposium Series on Computational Intelligence (SSCI), pages 01–07. IEEE. DOI: https://doi.org/10.1109/ssci50451.2021.9659984.