Uncovering the Potential of Children's Self-Regulation: Implementing Gamification Based on Deep Q-Network (DQN)

The article identifies a research gap in traditional methods of assessing children's self-regulation—one those techniques tend to be boring or fail. The study proposed to establish a validation framework of constructing the gamification model combined with Deep Q-Network (DQN) approach for evaluating self-regulation on children. The research question is how to incorporate up-to-date technology, mainly machine learning into a more playful and interactive self-regulation assessment designed for children. The approach is to exploit DQN in a maze game specifically for predicting the subsequent step that helps children complete this simple task with higher speed. This is then supported by the results, which back up that using DQN could reduce time for completing a game and in turn can make learning through gameplay more effective and fun with kids. The discussion indicates a promising role of DQN in improving children's learning processes and the assessment process of self-regulation. A gamification model on DQN can lead to valid self-regulation models, solution paths for educators and researchers. The author of the study recommends more research in larger populations and broader applications for education using DQN