Actor-Critic Reinforcement Learning for Personalized STEM Learning Path Optimization

Authors

  • Muhammad Hatta Universitas Catur Insan Cendekia, Indonesia
  • Lena Magdalena Universitas Catur Insan Cendekia, Indonesia
  • Dwi Pasha Anggara Putra Universitas Catur Insan Cendekia, Indonesia
  • Yohanes Michael Fouk Runa Universitas Catur Insan Cendekia, Indonesia
  • Ananda Irfansyah Universitas Catur Insan Cendekia, Indonesia
  • Fernando Valentino Universitas Catur Insan Cendekia, Indonesia
Pages Icon

DOI:

https://doi.org/10.51519/journalisi.v7i3.1270

Keywords:

Adaptive Learning, Reinforcement Learning, STEM Competency, Personalized Learning Paths, Non-Formal Education

Abstract

This study addresses the critical need for adaptive learning in non-formal education settings, particularly Community Learning Centres (PKBM) in Indonesia, where student heterogeneity and limited resources challenge conventional teaching methods. We developed a personalized learning path optimization model using Actor-Critic Reinforcement Learning (RL) to enhance STEM competency development. The novel framework integrates cognitive, affective, and personality features to dynamically adjust material difficulty based on real-time analysis of student cognitive states (quiz performance, completion rate) and affective conditions (emotional level), moving beyond static predictive approaches. Experimental results on a synthetic dataset demonstrate that the Actor-Critic agent achieves statistically significant higher rewards (-2.92 vs -3.01, p<0.05) and greater output stability compared to a random baseline. Although the absolute reward difference is modest, it reflects more consistent adaptive policy performance, despite limited effect size (Cohen's d=0.0317). Feature importance analysis confirms that quiz_score and emotion_level are the dominant factors influencing adaptive recommendations, while personality traits show negligible impact. The framework offers a viable pathway for scalable, personalized learning in resource-constrained environments. Future work should validate the model with real-world student data and refine reward functions to strengthen practical impact.

Downloads

Download data is not yet available.

References

E. Aymane, D. Aziz, H. Abdelfatteh, and A. Abdelhak, “Enabling sustainable learning: a machine learning approach for an eco-friendly multi-factor adaptive E-learning system,” Procedia Comput. Sci., vol. 236, pp. 533–540, 2024.

L. Major, G. A. Francis, and M. Tsapali, “The effectiveness of technology‐supported personalised learning in low‐ and middle‐income countries: A meta‐analysis,” Br. J. Educ. Technol., vol. 52, no. 5, pp. 1935–1964, Sept. 2021, doi: 10.1111/bjet.13116.

M. Taşkın, “Artificial Intelligence in Personalized Education: Enhancing Learning Outcomes Through Adaptive Technologies and Data-Driven Insights,” Hum. Comput. Interact., 2025, doi: 10.62802/ygye0506.

F. Naseer, M. N. Khan, M. Tahir, A. Addas, and S. M. H. Aejaz, “Integrating deep learning techniques for personalized learning pathways in higher education,” Heliyon, vol. 10, 2024, doi: 10.1016/j.heliyon.2024.e32628.

C.-J. Ku, K.-Y. Lin, H. Kwon, and T. R. Kelley, “A Six-Stage Instructional Design Model for Collaborative Implementation of Integrated STEM Education,” J. Technol. Educ., vol. 36, no. 2, pp. 25–60, 2025.

S. G. Essa, T. Çelik, and N. Human-Hendricks, “Personalized Adaptive Learning Technologies Based on Machine Learning Techniques to Identify Learning Styles: A Systematic Literature Review,” IEEE Access, vol. 11, pp. 48392–48409, 2023, doi: 10.1109/ACCESS.2023.3276439.

A. A. F. Osman, “A New Approach to Machine Learning Algorithms in Adaptive E-Learning Systems,” J. Inf. Syst. Eng. Manag., vol. 10, no. 15s, pp. 419–432, Mar. 2025, doi: 10.52783/jisem.v10i15s.2480.

Z. Ersozlu, S. Taheri, and I. Koch, “A review of machine learning methods used for educational data,” Educ. Inf. Technol., vol. 29, no. 16, pp. 22125–22145, 2024.

J. Xie, “The Role of Reinforcement Learning in Enhancing Education: Applications in Psychological Education and Intelligent Tutoring Systems,” Highlights Sci. Eng. Technol., 2025, doi: 10.54097/rkxbvk42.

C. W. Fernandes, T. Miari, S. Rafatirad, and H. Sayadi, “Unleashing the Potential of Reinforcement Learning for Enhanced Personalized Education,” in 2023 IEEE Frontiers in Education Conference (FIE), Oct. 2023, pp. 1–5, doi: 10.1109/FIE58773.2023.10342902.

Y. Li, “Research on the Optimization Path of Multi-scene Teaching Strategies for English in Higher Vocational Railway Industry Based on Reinforcement Learning,” J. Comb. Math. Comb. Comput., 2025, doi: 10.61091/jcmcc127b-007.

B. Fahad Mon, A. Wasfi, M. Hayajneh, A. Slim, and N. Abu Ali, “Reinforcement Learning in Education: A Literature Review,” Informatics, vol. 10, no. 3, p. 74, Sept. 2023, doi: 10.3390/informatics10030074.

A. Singla, A. N. Rafferty, G. Radanovic, and N. T. Heffernan, “Reinforcement Learning for Education: Opportunities and Challenges,” July 15, 2021, arXiv: arXiv:2107.08828, doi: 10.48550/arXiv.2107.08828.

X. Li, H. Xu, J. Zhang, and H. H. Chang, “Deep reinforcement learning for adaptive learning systems,” J. Educ. Behav. Stat., vol. 48, no. 2, pp. 220–243, 2023.

S. W. Sayed, A. M. Noeman, A. Abdellatif, M. Abdelrazek, M. G. Badawy, A. Hamed, and S. El-Tantawy, “AI-based adaptive personalized content presentation and exercises navigation for an effective and engaging E-learning platform,” Multimedia Tools Appl., vol. 82, no. 3, pp. 3303–3333, 2023.

R. Han, K. Chen, and C. Tan, “Curiosity-Driven Recommendation Strategy for Adaptive Learning via Deep Reinforcement Learning,” Oct. 12, 2019, arXiv: arXiv:1910.12577, doi: 10.48550/arXiv.1910.12577.

H. A. El-Sabagh, “Adaptive e-learning environment based on learning styles and its impact on development students’ engagement,” Int. J. Educ. Technol. High. Educ., vol. 18, no. 1, p. 53, Oct. 2021, doi: 10.1186/s41239-021-00289-4.

W. Strielkowski, V. Grebennikova, A. Lisovskiy, G. Rakhimova, and T. Vasileva, “AI‐driven adaptive learning for sustainable educational transformation,” Sustainable Development, vol. 33, no. 2, pp. 1921–1947, 2025.

F. Stasolla, A. Zullo, R. Maniglio, A. Passaro, M. Di Gioia, E. Curcio, and E. Martini, “Deep Learning and Reinforcement Learning for Assessing and Enhancing Academic Performance in University Students: A Scoping Review,” AI, vol. 6, no. 2, p. 40, 2025.

H. E. Sari, B. Tumanggor, and D. Efron, “Improving educational outcomes through adaptive learning systems using AI,” Int. Trans. Artif. Intell., vol. 3, no. 1, pp. 21–31, 2024.

C. Song, S. Y. Shin, and K. S. Shin, “Implementing the dynamic feedback-driven learning optimization framework: a machine learning approach to personalize educational pathways,” Appl. Sci., vol. 14, no. 2, p. 916, 2024.

S. Amin, M. I. Uddin, A. A. Alarood, W. K. Mashwani, A. Alzahrani, and A. O. Alzahrani, “Smart E-learning framework for personalized adaptive learning and sequential path recommendations using reinforcement learning,” IEEE Access, vol. 11, pp. 89769–89790, 2023.

R. Mustapha, S. Soukaina, Q. Mohammed, and A. Es-Sâadia, “Towards an adaptive e-learning system based on deep learner profile, machine learning approach, and reinforcement learning,” Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 5, 2023.

F. Rahioui, M. El Ghzaoui, M. A. T. Jouti, M. O. Jamil, and H. Qjidaa, “Machine Learning with Reinforcement for Optimal and Adaptive Learning,” in Int. Conf. Digital Technol. Appl., Jan. 2023, pp. 142–149. Cham: Springer Nature Switzerland.

F. Zini, F. Le Piane, and M. Gaspari, “Adaptive cognitive training with reinforcement learning,” ACM Trans. Interact. Intell. Syst., vol. 12, no. 1, pp. 1–29, 2022.

Downloads

Published

2025-09-30

Issue

Vol. 7 No. 3 (2025): September

Section

Articles

License

Authors Declaration

  1. The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
  2. The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
  3. The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
  4. The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
  5. The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
  6. The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
  7. If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
  8. The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights

How to Cite

[1]
M. Hatta, L. Magdalena, D. P. A. Putra, Y. M. F. Runa, A. Irfansyah, and F. Valentino, “Actor-Critic Reinforcement Learning for Personalized STEM Learning Path Optimization”, journalisi, vol. 7, no. 3, pp. 2780–2802, Sep. 2025, doi: 10.51519/journalisi.v7i3.1270.

Most read articles by the same author(s)