“Real-Time Wireless Adaptive Learning Systems Using Reinforcement Learning and IoT for Smart Education”

This study developed an adaptive learning system based on reinforcement learning and IoT technologies, aiming to enhance personalization and teaching efficiency in online learning. The system collects real-time student data, such as quiz accuracy, study duration, and interaction frequency, through IoT devices, and dynamically adjusts the teaching content using the Q-learning algorithm. Simulated experiments were conducted to evaluate the system's learning path optimization and progress adjustment effects. The results demonstrate that the system significantly reduces students’ learning time, improves quiz accuracy, and maintains real-time responsiveness to teaching feedback. Compared to existing literature, this system shows a notable advantage in personalized learning path optimization and real-time feedback. Additionally, the system's performance remained stable and efficient under varying data volumes and learning difficulties. This study provides new possibilities for personalized learning and intelligent feedback mechanisms in future smart education, promoting further advancements in intelligent and personalized online education.