Article: DRL-MusicEdu: a deep reinforcement learning-based dynamic music teaching recommender system Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.45 pp.1 - 16 Abstract: Addressing the inability of traditional music teaching systems to dynamically adapt to learners' personalised states, this study proposes deep reinforcement learning-MusicEdu - a dynamic recommender system based on deep reinforcement learning. The framework constructs an intelligent agent that continuously perceives multidimensional learner states (skill proficiency, interests, fatigue) and dynamically optimises teaching-resource sequences via deep reinforcement learning (using proximal policy optimisation). This leverages a structured resource library derived from the Lakh Musical Instrument Digital Interface Dataset, annotated with metadata including difficulty, style, and technical attributes. Experimental validation across 20 weeks with five learner profiles demonstrates that deep reinforcement learning-MusicEdu significantly outperforms baselines, improving skill growth rate by 19.2% (<i>p</i> < 0.01) and user retention by 18.1%. The system enables personalised adaptive learning pathways, establishing an innovative decision-making framework for intelligent music education. Inderscience Publishers - linking academia, business and industry through research

Title: DRL-MusicEdu: a deep reinforcement learning-based dynamic music teaching recommender system

Authors: Pengfei Wu; Ruixue Sun; Wu Jun

Addresses: College of Music and Dance, Qiqihar University, Qiqihar, 161000, China ' Arts Department, Qinhuangdao Vocational and Technical College, Qinhuangdao, 066100, China ' Teaching Affairs Office, Qinhuangdao Open University, Qinhuangdao, 066000, China

Abstract: Addressing the inability of traditional music teaching systems to dynamically adapt to learners' personalised states, this study proposes deep reinforcement learning-MusicEdu - a dynamic recommender system based on deep reinforcement learning. The framework constructs an intelligent agent that continuously perceives multidimensional learner states (skill proficiency, interests, fatigue) and dynamically optimises teaching-resource sequences via deep reinforcement learning (using proximal policy optimisation). This leverages a structured resource library derived from the Lakh Musical Instrument Digital Interface Dataset, annotated with metadata including difficulty, style, and technical attributes. Experimental validation across 20 weeks with five learner profiles demonstrates that deep reinforcement learning-MusicEdu significantly outperforms baselines, improving skill growth rate by 19.2% (p < 0.01) and user retention by 18.1%. The system enables personalised adaptive learning pathways, establishing an innovative decision-making framework for intelligent music education.

Keywords: deep reinforcement learning; DRL; music education; personalised recommendations; Lakh MIDI Dataset; adaptive learning.

DOI: 10.1504/IJICT.2025.150415

International Journal of Information and Communication Technology, 2025 Vol.26 No.45, pp.1 - 16

Received: 10 Aug 2025
Accepted: 26 Sep 2025
Published online: 12 Dec 2025 *

Title: DRL-MusicEdu: a deep reinforcement learning-based dynamic music teaching recommender system

Keep up-to-date