The impact of AI use on the performance of chess engines
Article Sidebar
Open full text
Issue Vol. 37 (2025)
-
Performance evaluation of Machine Learning and Deep Learning models for 5G resource allocation
Abdullah Havolli, Majlinda Fetaji371-378
-
Analysis of the use of object detection systems in edge computing
Jakub Kozłowski, Marcin Badurowicz379-390
-
Performance analysis of Jetpack Compose components in mobile applications
Adrian Kwiatkowski, Jakub Smołka391-398
-
Methods for comparing three-dimensional motion trajectories
Tomasz Waldemar Samorow, Maria Skublewska-Paszkowska399-404
-
Performance and scalability analysis of monolithic and microservice architectures in social networks
Viacheslav Chernohor405-409
-
Comparative analysis of methods for identifying tree structures of coronary vessels
Kacper Liżewski, Małgorzata Charytanowicz410-417
-
Websites accessibility assessment of voivodeship cities in Poland
Kacper Czajka, Maria Skublewska-Paszkowska418-425
-
Analysis of ORM framework approaches for Node.js
Serhii Zhadko-Bazilevych426-430
-
Analysis of performance optimization methods for 3D games in the Unity environment
Maciej Potręć, Marcin Badurowicz431-435
-
The impact of AI use on the performance of chess engines
Jakub Król, Jakub Smołka436-442
-
Evaluating the effectiveness of selected tools in recognizing emotions from facial photos
Klaudiusz Wierzbowski443-450
-
Performance analysis of the GraphQL API creation technologies using Spring Boot and NestJS
Jakub Maciej Tkaczyk, Beata Pańczyk451-456
-
Comparative Performance Analysis of RabbitMQ and Kafka Message Queue Systems in Spring Boot and ASP.NET Environments
Filip Kamiński, Radosław Kłonica, Beata Pańczyk457-462
-
Analysis of current threats and security measures used in web applications on the example of Symfony, Express, and Spring Boot
Karol Kurowski, Magdalena Kramek463-469
-
The use of machine learning to classify symbols on cultural monuments to identify their origin and historical period.
Igor Pajura, Sylwester Korga470-475
-
Investigating Machine Learning Algorithms for Stroke Occurrence Prediction
Kazeem B. Adedeji, Titilayo A. Ogunjobi, Thabane H. Shabangu, Joshua A. Omowaye476-483
-
Comparative performance analysis of Spring Boot and Quarkus frameworks in Java applications
Grzegorz Szymanek, Jakub Smołka484-491
-
Influence of activation function in deep learning for cutaneous melanoma identification
Adrian Szymczyk, Maria Skublewska-Paszkowska492-499
-
Analysis of methods for simulating character encounters in a game with RPG elements
Michał Zdybel, Jakub Smołka500-507
-
Analysis of the efficiency of Apex and Java languages and related technologies in performing database operations
Marcin Janczarek, Konrad Lewicki, Jakub Smołka508-514
Main Article Content
DOI
Authors
Abstract
This paper presents a comprehensive comparative analysis of chess engines with particular focus on artificial intelligence technologies used in their implementation. Six engines were examined, representing various algorithmic approaches – from classical heuristic methods to advanced neural networks and reinforcement learning. Experiments were conducted for three different starting positions and with three time controls. The results clearly indicate the superiority of engines utilizing advanced machine learning techniques, which achieved the highest effectiveness in all tested conditions. The conducted research provides valuable information about the impact of applied AI technologies on the playing strength of chess engines in diverse conditions.
Keywords:
References
[1] A. Elo, The Proposed USCF Rating System, Its Deve-lopment, Theory, and Applications, Chess Life 22 (1967) 242–247.
[2] M. Sójka, Performance Comparison Between Selected Chess Engines, Journal of Computer Sciences Institute 24 (2022) 228–235.
[3] Strona lichess.org, zasady wariantu chess960, https://lichess.org/variant/chess960, [01.07.2025].
[4] D. Silver, T. Hubert, J. Schrittwieser, A General Reinfor-cement Learning Algorithm That Masters Chess, Shogi, and Go Through Self-Play, Science 362 (2018) 1140–1144, https://doi.org/10.1126/science.aar6404.
[5] T. Zahavy, V. Veeriah, S. Hou, Diversifying AI: Towards Creative Chess With AlphaZero, arXiv (2023), https://doi.org/10.48550/arXiv.2308.09175.
[6] W. B. Putra, L. Heryawan, Applying Alpha-Beta Algo-rithm in a Chess Engine, Jurnal Teknosains 6 (2016) 37–43.
[7] M. Block, M. Bader, E. Tapia, Using Reinforcement Learning in Chess Engines, Research in Computing Science 35 (2008) 31–40.
[8] Y. Nasu, Efficiently Updatable Neural-Network-Based Evaluation Functions for Computer Shogi, In The 28th World Computer Shogi Championship Appeal Document (2018) 185.
[9] S. Y. G. Chi, Exploring the Performance of Deep Resi-dual Networks in Crazyhouse Chess, arXiv (2019), https://doi.org/10.48550/arXiv.1908.09296.
[10] Q. A. Sadmine, A. Husna, M. Müller, Stockfish or Leela Chess Zero? A Comparison Against Endgame Tablebases, In Advances in Computer Games, Springer Nature Switzerland (2023) 26–35.
[11] Strona internetowa programu Lucas Chess, https://lucaschess.pythonanywhere.com, [01.07.2025].
[12] Strona internetowa silnika szachowego Stockfish, https://stockfishchess.org, [01.07.2025].
[13] Strona internetowa silnika szachowego Lc0, https://lczero.org, [01.07.2025].
[14] Strona internetowa silnika szachowego Komodo Dragon, https://komodochess.com, [01.07.2025].
[15] Geneza i opis silnika szachowego Houdini, https://www.chessprogramming.org/Houdini, [01.07.2025].
Article Details
Abstract views: 20

