Abstract

The current advancement in computational technologies in education and learning techniques is being profoundly altered by artificial intelligence and machine learning. Students are encouraged to learn on their own. To provide personalized learning experiences, this study introduces an AI-driven adaptive learning system that combines generative AI (GPT model) with Q-Learning, a powerful reinforcement learning algorithm. Depending on the learner’s success, the experimental system adjusts the context order and the level of difficulty (Easy, Medium, Hard) of the questions. The constant accessibility of various e-learning platforms is a major benefit. The in-memory backend of the system enables simple and quick changes. Additional relevant ideas and perspectives on the topic might be offered. This improves cognitive function, which in turn improves performance and learning. Numerous gamification elements are integrated into the system, such as badges that may be earned and leaderboards that show individual performance indicators. The goal is to increase general enthusiasm. The simulated evaluation demonstrates improvements in adaptive sequencing, response latency, and mastery metrics under controlled conditions. Compared to conventional e-learning techniques, this method increases student engagement in the learning process and promotes higher knowledge retention. This study offers a scalable competency-based framework that promotes learner-centered, data-informed instructional models in academic and professional training settings by methodically evaluating the combination of educator-led knowledge with AI-driven flexibility.

Authors

Vinit Kumar Shukla¹, Seshaiah Merikapudi²
Nagarjuna College of Engineering and Technology, India¹, S.J.C. Institute of Technology, India²

Keywords

Q-Learning, In-Memory Architecture, Adaptive Learning, Gamification, Knowledge Retention