Heuristic Optimization of a Tetris Bot Using Genetic Algorithms: An Adaptive Evolutionary Approach

Year 2026, Volume: 18 Issue: 1, 220 - 247, 23.02.2026

Ercan Erkalkan

https://doi.org/10.47000/tjmcs.1663275

https://izlik.org/JA57WU83AS

Abstract

This study presents a Genetic Algorithm (GA)-driven optimization framework for enhancing the heuristic evaluation function of a Tetris bot. The proposed approach combines offline evolutionary training with real-time dynamic weight adjustments to adapt the bot's strategy to evolving gameplay conditions. Key heuristic features—including hole minimization, line clearing, and surface bumpiness—are weighted dynamically based on board state metrics such as maximum column height. Evaluated through 100 independent simulations, the GA-optimized bot demonstrated significant performance improvements over a baseline bot with fixed heuristic weights: +61.79\% in average lines cleared (91.38 vs. 56.48) and +55.74\% in average game duration (3.17 vs. 2.04 minutes). While decision latency increased marginally (7.33 ms vs. 7.05 ms), this trade-off was justified by the bot's enhanced strategic adaptability, evidenced by reduced performance variance and outlier frequency. The results validate GA's efficacy in optimizing complex, multi-objective decision-making processes in dynamic environments. Future work will explore hybrid GA-reinforcement learning architectures and applications to other real-time strategy games.

Keywords

tetris bot , genetic algorithms , heuristic optimization , dynamic weighting , evolutionary computation

References

• Ade, P., Implementation of genetic algorithms in the application of car racing games, Indonesian Journal of Artificial Intelligence and Data Mining, 4(2021), 29–34.
• Angeline, P.J., Kinnear, K.E., Genetically optimizing the speed of programs evolved to play tetris, in: Advances in Genetic Programming, MIT Press, 1996, 279–298.
• Armanto, H., Setiabudi, K., Pickerling, C., Komparasi algoritma WOA, MFO dan genetic pada optimasi evolutionary neural network dalam menyelesaikan permainan 2048, Jurnal Inovasi Teknologi dan Edukasi Teknik, (2021).
• Armanto, H., Rosyid, H.A., Muladi, G., Improved non-player character (NPC) behavior using evolutionary algorithm—A systematic review, Entertainment Computing, 52(2025), 100875.
• Armanto, H., Dwi Putra, R., Pickerling, C., MVPA and GA comparison for state space optimization at classic tetris game agent problem, Inform: Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, 7(2022), 73–80.
• Bairaktaris, J.A., Johannssen, A., Outsmarting algorithms: A comparative battle between reinforcement learning and heuristics in atari tetris, Expert Systems with Applications, 277(2025), 127251.
• Bello Salau, H., Aibinu, A., Onwuka, L., Onumanyi, A., Dukiya, J., An examination of different selection approaches for genetic algorithm implementation process, Proc. IEEE NIGERCON, (2018), 123–126.
• Bernal, G., Jung, H., Yassı, I.E., Hidalgo, N., Alemu, et al., Unraveling the dynamics of mental and visuospatial workload in virtual reality environments, Computers, 13(2024), 246.
• Connor, A.M., Greig, T.J., Kruse, J., Evolutionary generation of game levels, EAI Endorsed Transactions on Creative Technologies, 5(2018).
• Da Col, G., Teppan, E.C., Heuristic Search for Tetris: A Case Study, in: Intelligent Computing, Springer, Cham, 2019.
• Da Silva, R.S., Stubs Parpinelli, R., Playing the original game boy tetris using a real coded genetic algorithm, Proc. BRACIS, (2017), 282–287.
• Dasari, V., Im, M.S., Geerhart, B., Complexity and mission computability of adaptive computing systems, The Journal of Defense Modeling & Simulation, 17(2019), 1–7.
• Dirik, M., Comparison of recent meta-heuristic optimization algorithms using different Benchmark functions, Journal of Mathematical Sciences and Modelling, 5(2022), 113–124.
• Fisher, N., Kulshreshth, A.K., Exploring dynamic difficulty adjustment methods for video games, Virtual Worlds, 3(2024), 230–255.
• Gabillon, V., Ghavamzadeh, M., Scherrer, B., Approximate dynamic programming finally performs well in the game of Tetris, Proc. NIPS, (2013), 1754–1762.
• Hafis, M., Tolle, H., Supianto, A., A literature review of empirical evidence on procedural content generation in game-related implementation, Journal of Information Technology and Computer Science, 4(2019), 185–192.
• Hassanat, A., Almohammadi, K., Alkafaween, E., Abunawas, E., Hammouri, A., Prasath, V.B.S., Choosing mutation and crossover ratios for genetic algorithms—A review with a new dynamic approach, Information, 10(2019), 390.
• Im, M.S., Dasari, V., Genetic optimization algorithms applied toward mission computability models, Military Operations Research, 35(2020), 1–11.
• Joseph, M., Emergent Behaviour in Game AI: A Genetic Programming and CNN-based Approach to Intelligent Agent Design, Ph.D. Thesis, Brock University, 2023.
• Juvina, I., O’Neill, K., Carson, J., Menke, P., Wong, C.H. et al., Human-AI Coordination to Induce Flow in Adaptive Learning Systems, in: AI Approaches for Designing and Evaluating Interactive Intelligent Systems, Springer, 2024.
• Konak, A., Kulturel-Konak, S., Regret-based Nash equilibrium sorting genetic algorithm for combinatorial game theory problems with multiple players, Evolutionary Computation, 30(2022), 447–478.
• Kruse, J., Connor, A.M., Marks, S., Evaluation of a multi-agent human-in-the-loop game design system, ACM Trans. Interact. Intell. Syst., 12(2022), 19.
• Müller-Brockhausen, M., Preuss, M., Plaat, A., A new challenge: Approaching tetris link with AI, Proc. IEEE Conf. on Games, (2021), 1–8.
• Papazoglou, G., Biskas, P.N., Review and comparison of genetic algorithm and particle Swarm optimization in the optimal power flow problem, Energies, 16(2023), 1152.
• Parker-Holder, J., Rajan, R., Song, X., Biedenkapp, A., Miao, Y. et al., Automated reinforcement learning (AutoRL): A survey and open problems, Journal of Artificial Intelligence Research, 74(2022), 517–568.
• Phon-Amnuaisuk, S., em GA-Tetris Bot: Evolving a Better Tetris Gameplay Using Adaptive Evaluation Scheme, in: Neural Information Processing, Springer, Cham, 2014.
• Pickering, L., Cohen, K., Genetic Fuzzy Systems: Genetic Fuzzy Based Tetris Player, in: Fuzzy Information Processing 2020, Springer, Cham, 2022.
• Quintero Lorza, D.P., Duque M´endez, N.D., G´omez Soto, J.A., GLORIA: A Genetic Algorithms Approach to Tetris, in: Advances and Applications in Computer Science, Electronics and Industrial Engineering, Springer, Cham, 2020.
• Rawat, B., Duwal, D., Phuyal, S., Pant, A., A comparative review between various selection techniques in genetic algorithm for finding optimal solutions, International Journal of Computer Sciences and Engineering, 10(2022), 15–22.
• Riedel, J., Blum, S., Puisa, R., Wintermantel, M., Adaptive mutation strategies for evolutionary algorithms: A comparative Benchmark study, Proc. Weimarer Optimierungs- und Stochastiktage 2.0, Weimar, 2005.
• Sta´nczak, J.T., Efficient selection methods in evolutionary algorithms, Computer Science, 25(2024), 95–122.
• Strauch, C., Barthelmaes, M., Altgassen, E., Huckauf, A., Pupil dilation fulfills the requirements for dynamic difficulty adjustment in gaming on the example of Pong, Proc. ACM ETRA, (2020), 19.
• Tao, J., Wu, G., Yi, Z., Zeng, P., Innovative application of genetic algorithms in the computer games, Proc. CCDC, (2021), 2197–2200.
• Thang, T.B., Dao, T.C., Long, N.H., Binh, H.T.T., Parameter adaptation in multifactorial evolutionary algorithm for many-task optimization, Memetic Computing, 13(2021), 433–446.
• Tasgetiren, M.F., Liang, Y.-C., Sevkli, M., Gencyilmaz, G., Particle swarm optimization and differential evolution for the single machine total weighted tardiness problem, International Journal of Production Research, 44(2006), 4737–4754.
• Vani, R., Vyas, T., Tahilramani, N., CBIR Using SVM, Genetic algorithm, Neural Network, Fuzzy Logic, Neuro-fuzzy Technique: A Survey, Proc. IC3IoT, (2018), 239–242.
• Vardal, O., Using Video Games to Study the Acquisition and Performance of Psychomotor Skills, Ph.D. Thesis, University of York, 2023.
• Wang, P., Zeng, Y., Chen, B., Cao, L., A Data-driven approach to solve a production constrained build-order optimization problem, Proc. CCC, (2019), 2692–2697.
• Xia, Z., Optimizing Learned Networking Rate Adaptation via Guided Reward Reweighting, Ph.D. dissertation, University of Chicago, 2024.
• Zhu, Q., Wu, X., Lin, Q., Ma, L., Li, J., Ming, Z., Chen, J., A survey on evolutionary reinforcement learning algorithms, Neurocomputing, 556(2023), 126628.