Maximum-continue Learning: Recognition Appropriate Genre for Educational Video Games with Multi-agent Approach

In recent years, the application of electronic media in the educational process has been the focus of many researchers. To this purpose, one of the most effective tools that could be considered is serious games and it’s utilization for the purpose of education is called game-based learning. The video games can be developed in 2D and 3D perspective each of which includes several genres and the most popular 3D video game perspectives regardless of its genre are First-Person, Third-Person and omnipresent perspectives. Many studies have shown that video games are almost the most effective way to teach concepts to learners but only few researches was conducted on the impact of the game genres in the rate of knowledge transfer. Also, in none of these studies did the authors consider game’s engagement flow and knowledge transfer rate together. In this study we intend to propose a framework called Maximum-Continues Learning (MCL) in context of a multi-agent system which is composed of two agents: student and teacher. MCL aims to explore genre or genre combination for developing procedural educational games that can satisfy both agents as much as possible. In order to further clarity about this framework, we developed a 11-level game with ability to run in three mentioned genres for each level and based on the player’s choice and then with participation of 10 students to play this game, we found that the combination of 48% third-person and 52% strategic genres can provide the maximum-fairest satisfaction for both student and teacher.

کلیدواژه ها:

Serious games ، Genre preferences ، Education ، Measurement index ، Multi-agent systems ، MCL