Scholarlink

<p>Mental health education enhances resilience and reduces stress, but traditional institutions often struggle to allocate resources to diverse learners. Existing systems employ static recommendation models, which fail to account for user demands and engagement levels. MIND-RARE (Mental Health Intervention Dynamic—Reinforcement Learning-based Adaptive Resource Engagement) is a reinforcement learning-optimized method for dynamic resource allocation decision-making in adaptive, individualized psychological health education. The primary goal is to develop a framework that dynamically allocates instructional resources to optimize stress reduction and resource utilization. User demographic information, baseline stress and resilience scores, and behavioral feedback are used in reinforcement learning. In a hierarchical RL model with constraint optimization, the state space represents user conditions, the action space allocates educational content, and the reward function maps stress reduction. Results show that the MIND-RARE framework promotes personalization by suggesting interventions that match learner profiles. The dynamic allocation technique increased engagement and optimized resource use under limits. Findings reveal that MIND-RARE reduced stress more effectively than baseline suggestion approaches while maintaining fairness across user groups. The system adapted well to user conditions and resource availability. Ultimately, the MIND-RARE framework enables tailored and resource-efficient decision-making for mental health education.</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

Dynamic resource allocation decision-making mechanism for mental health education optimized by reinforcement learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月27日

查看全文
  • Yuxuan Wu,
  • Lin Xu

摘要

Mental health education enhances resilience and reduces stress, but traditional institutions often struggle to allocate resources to diverse learners. Existing systems employ static recommendation models, which fail to account for user demands and engagement levels. MIND-RARE (Mental Health Intervention Dynamic—Reinforcement Learning-based Adaptive Resource Engagement) is a reinforcement learning-optimized method for dynamic resource allocation decision-making in adaptive, individualized psychological health education. The primary goal is to develop a framework that dynamically allocates instructional resources to optimize stress reduction and resource utilization. User demographic information, baseline stress and resilience scores, and behavioral feedback are used in reinforcement learning. In a hierarchical RL model with constraint optimization, the state space represents user conditions, the action space allocates educational content, and the reward function maps stress reduction. Results show that the MIND-RARE framework promotes personalization by suggesting interventions that match learner profiles. The dynamic allocation technique increased engagement and optimized resource use under limits. Findings reveal that MIND-RARE reduced stress more effectively than baseline suggestion approaches while maintaining fairness across user groups. The system adapted well to user conditions and resource availability. Ultimately, the MIND-RARE framework enables tailored and resource-efficient decision-making for mental health education.