Abstract
Mobile games represent a killer application that is attracting millions of subscribers worldwide. One of the aspects crucial to the commercial success of a game is ensuring an appropriately challenging artificial intelligence (AI) algorithm against which to play. However, creating this component is particularly complex as classic search AI algorithms cannot be employed by limited devices such as mobile phones or, even on more powerful computers, when considering imperfect information games (i.e., games in which participants do not a complete knowledge of the game state at any moment). In this paper, we propose to solve this issue by resorting to a machine learning algorithm which uses profiling functionalities in order to infer the missing information, thus making the AI able to efficiently adapt its strategies to the human opponent. We studied a simple and computationally light machine learning method that can be employed with success, enabling AI improvements for imperfect information games even on mobile phones. We created a mobile phone-based version of a game calledGhostsand present results which clearly show the ability of our algorithm to quickly improve its own predictive performance as far as the number of games against the same human opponent increases.
Highlights
Mobile phones have brought into our lives the possibility and the willingness to be always reachable by anybody; they have almost become an extension of ourselves, making us Homo Mobilis for how much we tend to never separate from them [1]
If a mobile game producer decides to create a game with only one connectivity option, we deem that the chosen one should be Bluetooth as it is available on almost any new mobile phone and its use is free of charge
The mass adoption of mobile phones in our society has transformed them from gadgets into commodities
Summary
Mobile phones have brought into our lives the possibility and the willingness to be always reachable by anybody; they have almost become an extension of ourselves, making us Homo Mobilis for how much we tend to never separate from them [1]. It associates the behavior features of a player with a presumed type of a piece; by observing how a player acts in different game state configurations, the AI becomes able to classify tactics employed by that player and to adapt to them Even if this AI solution represents our main scientific contribution, while creating our mobile version of the game Ghosts, we have not overlooked at two practical problems that are crucial in the successful deployment of a real mobile game: (i) compatibility with the highest number of mobile phones in the market and (ii) connectivity among players’ mobile phones [5].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
