| Issue |
ITM Web Conf.
Volume 73, 2025
International Workshop on Advanced Applications of Deep Learning in Image Processing (IWADI 2024)
|
|
|---|---|---|
| Article Number | 01023 | |
| Number of page(s) | 7 | |
| Section | Reinforcement Learning and Optimization Techniques | |
| DOI | https://doi.org/10.1051/itmconf/20257301023 | |
| Published online | 17 February 2025 | |
Innovative applications and challenges of dobby slot machine algorithms in online gaming
School of Computer Science, University of Hull, Kingston upon Hull, HU6 7EL, United Kingdom
* Corresponding author: L.YANG2-2023@hull.ac.uk
With the rapid development of the online gaming industry, how to improve user experience, optimise game design and increase business revenue through intelligent algorithms has become a key issue in the industry. The Multi-armed Gambling Machine (MAB) algorithm, as a classic reinforcement learning problem, has shown great potential for decision optimisation in online games. By balancing the strategy of ‘ exploration and development ’ , the MAB algorithm gradually optimises decision making in an uncertain environment, enhancing the personalised gaming experience, optimising the economic system and improving player retention. This paper reviews the innovative application of the MAB algorithm in online games, focuses on its application in game design, personalised recommendation, game economic system and player retention optimisation, discusses the challenges of the MAB algorithm in practical application and proposes future research directions. Through an overview of existing research results, this paper aims to provide a comprehensive perspective for academia and industry to promote the further development and application of the MAB algorithm in online games.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.