Strategy adaptive system to learning processes for emerging serious games using a fuzzy classifier system

Abstract

An emerging serious game (ESG) is a game that unfolds autonomously without explicit laws, adapting to the player, where the player learns while playing. An ESG engine must enable the emergence in the game, in order to allow its adaptation to the specific environment where it is being used. In previous articles, different components of an ESG engine have been proposed. This paper proposes a strategy adaptive system (SAS) for ESG, which allows the emergence of strategies in a videogame. Particularly, SAS manages the emergence of new procedures or methods (tactics), as well as actions (logistics), among other things, in the ESG, to adapt it to the environment. This component is based on a Fuzzy Classifier System that generates new rules, tactics, etc. in the game to follow the desired behavior. In this article, SAS is applied in a smart classroom (SaCI, for its acronym in Spanish), in such a way that allows the adaptation of an ESG to the students in SaCI. Especially, it is used during their teaching-learning processes. Additionally, this paper analyzes the performance of SAS in SaCI, with very encouraging results, since the quality of the strategies proposed by SAS (defined by rules that define the logic and tactics of the game) is improved in all case studies. This improvement is confirmed because the average use of the rules generated by our adaptive system is greater than 3.6, when the initial rules are used on average less than once.