Scholarlink

<p>Virtual Reality (VR) has emerged as a powerful educational tool capable of creating immersive and interactive learning environments, yet most existing VR systems lack adaptive mechanisms, individualized feedback, and support for the diverse cognitive and emotional needs of learners, particularly in home-based family education contexts. This study introduces a reinforcement learning (RL)–enhanced VR platform designed to dynamically adjust instructional content, difficulty levels, and learning trajectories based on each learner’s performance, engagement, and working pace. The RL model continuously monitors user actions, optimizes content sequencing, and delivers targeted real-time feedback to reduce learner confusion, maintain progress, and improve instructional effectiveness. A quasi-experimental evaluation with 50 participants demonstrated substantial improvements over a traditional VR environment, with engagement increasing by 20 percent, task completion improving by 15 percent, and knowledge retention rising by 25 percent. These results validate the effectiveness of integrating RL-driven adaptivity into immersive VR learning systems. The proposed platform’s distinguishing capability lies in its ability to provide individualized support and real-time instructional adjustments, thereby offering a more responsive and personalized learning experience for diverse learners in family settings. This work contributes a scalable framework for intelligent adaptive VR education and demonstrates its potential to transform home-based learning into a more effective, supportive, and high-impact process.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Reinforcement learning enhanced virtual reality training in intelligent family education platforms

  • 期刊论文

  • 发表日期：

    2026年3月20日

查看全文
  • Tian Shaowei,
  • Liu Juan

摘要

Virtual Reality (VR) has emerged as a powerful educational tool capable of creating immersive and interactive learning environments, yet most existing VR systems lack adaptive mechanisms, individualized feedback, and support for the diverse cognitive and emotional needs of learners, particularly in home-based family education contexts. This study introduces a reinforcement learning (RL)–enhanced VR platform designed to dynamically adjust instructional content, difficulty levels, and learning trajectories based on each learner’s performance, engagement, and working pace. The RL model continuously monitors user actions, optimizes content sequencing, and delivers targeted real-time feedback to reduce learner confusion, maintain progress, and improve instructional effectiveness. A quasi-experimental evaluation with 50 participants demonstrated substantial improvements over a traditional VR environment, with engagement increasing by 20 percent, task completion improving by 15 percent, and knowledge retention rising by 25 percent. These results validate the effectiveness of integrating RL-driven adaptivity into immersive VR learning systems. The proposed platform’s distinguishing capability lies in its ability to provide individualized support and real-time instructional adjustments, thereby offering a more responsive and personalized learning experience for diverse learners in family settings. This work contributes a scalable framework for intelligent adaptive VR education and demonstrates its potential to transform home-based learning into a more effective, supportive, and high-impact process.