Research on Personalized Art Learning Path Recommendation Algorithm Based on Reinforcement Learning
DOI:
https://doi.org/10.67541/jdc2603Keywords:
Reinforcement learning; Personalized learning path recommendation; Graph attention network; Art education; Deep Q networkAbstract
In online art education, the learning path has strong non-linear dependence and significant individual differences. Traditional sequential recommendation methods are inefficient because they struggle to dynamically model the skill topological constraints. This paper proposes a personalized art learning path recommendation algorithm named Art-DQN, which integrates graph attention networks and improved deep Q networks. Firstly, an art skill directed topological graph is constructed, and the graph attention network is used to extract high-order neighborhood features of the learner's skill state; Secondly, a dual-channel feature fusion module is designed, combining the skill graph features with the behavior sequence features encoded by LSTM and inputting them into the Q network; Finally, an ε-greedy exploration strategy based on skill topological constraints and a prioritized experience replay mechanism are proposed. Experiments on a dataset containing 500 real learners' logs and 1000 simulation trajectories show that the average skill mastery time of Art-DQN is 32.4 steps, which is 22.3% lower than that of the standard DQN, the target skill achievement rate reaches 92%, the number of prerequisite violations is 0, the path redundancy is as low as 0.09, and the convergence speed is increased by 41%. Ablation experiments verify the independent contributions of the dual-channel fusion and dynamic reward weights, and parameter sensitivity analysis and robustness tests further prove the stability of the algorithm. This algorithm provides an effective solution that combines structural constraints and personalized adaptation for intelligent recommendation in art education.
References
[1] Savage, T. (2024). Teaching to the line: how do visual arts technicians in higher education conceive of their pedagogies? (Doctoral dissertation, University for the Creative Arts). https://doi.org/10.13140/RG.2.2.18860.99203
[2] Shao, J. (2024). Personalized Learning for Art Major Students Based on Learner Characteristics (Doctoral dissertation, Chapman University). https://doi.org/10.36837/chapman.000560
[3] Ткач, М., Олексюк, О. М., Бобик, Л., Мимрик, М., & Вей, Л. (2024). Non-linear thinking strategies in post-non-classical higher art education: A synergistic concept. Scientific Herald of Uzhhorod University, 55, 1994-2005. https://doi.org/10.54919/physics/55.2024.199kv4
[4] Li, Y., & Shi, J. (2025). Multimodal deep learning for art behavior analysis and personalized teaching path generation. Discover Artificial Intelligence, 5(1), 215. https://doi.org/10.1007/s44163-025-00480-w
[5] Shokrzadeh, Z., Feizi-Derakhshi, M. R., Balafar, M. A., & Mohasefi, J. B. (2024). Knowledge graph-based recommendation system enhanced by neural collaborative filtering and knowledge graph embedding. Ain Shams Engineering Journal, 15(1), 102263. https://doi.org/10.1016/j.asej.2023.102263
[6] Troussas, C., & Krouska, A. (2022). Path-based recommender system for learning activities using knowledge graphs. Information, 14(1), 9. https://doi.org/10.3390/info14010009
[7] Qian, D., & Luo, W. (2026). Revolutionizing arts education through 3D virtual reality: a mixed-method analysis of its impact on sculpting and carving skills among undergraduate art students. Educational technology research and development, 1-36. 1001-1036 https://doi.org/10.1007/s11423-025-10584-w
[8] Du, W., Zhao, Y., Wang, Y., Wang, H., & Yang, M. (2022). Novel machine learning approach for shape-finding design of tree-like structures. Computers & Structures, 261, 106731. https://doi.org/10.1016/j.compstruc.2021.106731
[9] Zhao, L. T., Wang, D. S., Liang, F. Y., & Chen, J. (2023). A recommendation system for effective learning strategies: An integrated approach using context-dependent DEA. Expert Systems with Applications, 211, 118535. https://doi.org/10.1016/j.eswa.2022.118535
[10] Garg, S., & Roy, D. (2022). A birds eye view on knowledge graph embeddings, software libraries, applications and challenges. arXiv preprint arXiv:2205.09088. https://doi.org/10.48550/arXiv.2205.09088
[11] Wani, A. A. (2025). Comprehensive review of dimensionality reduction algorithms: challenges, limitations, and innovative solutions. PeerJ Computer Science, 11, e3025. https://doi.org/10.7717/peerj-cs.3025
[12] Wang, Z., Li, S., Liu, Q., Pan, Z., & Sun, X. (2026). MKAN-Refine: Fine-Grained Crisis Information Mining via Reliability-Aware Nonlinear Refinement and Kolmogorov–Arnold Networks. IEEE Access. https://doi.org/10.1109/access.2026.3688494
[13] Li, P., & Ding, Z. (2025). Application of deep learning-based personalized learning path prediction and resource recommendation for inheriting scientist spirit in graduate education. Computer Science and Information Systems, (00), 43-43. https://doi.org/10.2298/csis241125043l
[14] Angelaki, S., Triantafyllidis, G. A., & Besenecker, U. (2022). Lighting in kindergartens: Towards innovative design concepts for lighting design in kindergartens based on children’s perception of space. Sustainability, 14(4), 2302. https://doi.org/10.3390/su14042302
[15] Newbury, R., Gu, M., Chumbley, L., Mousavian, A., Eppner, C., Leitner, J., ... & Cosgun, A. (2023). Deep learning approaches to grasp synthesis: A review. IEEE Transactions on Robotics, 39(5), 3994-4015. https://doi.org/10.48550/arXiv.2207.02556
[16] Bai, Y., Liu, Z., Guo, T., Hou, M., & Xiao, K. (2025). Prerequisite relation learning: a survey and outlook. ACM Computing Surveys, 57(11), 1-28. https://doi.org/10.1145/3733593
[17] Wang, Z., Yan, W., Zeng, C., Tian, Y., & Dong, S. (2023). A unified interpretable intelligent learning diagnosis framework for learning performance prediction in intelligent tutoring systems. International Journal of Intelligent Systems, 2023(1), 4468025. https://doi.org/10.1155/2023/4468025
[18] Winget, M., & Persky, A. M. (2022). A practical review of mastery learning. American journal of pharmaceutical education, 86(10), ajpe8906. https://doi.org/10.5688/ajpe8906
[19] Yu, S., Zeng, Y., Yang, F., & Pan, Y. (2024, March). Causal-driven skill prerequisite structure discovery. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 38, No. 18, pp. 20604-20612). https://doi.org/10.1609/aaai.v38i18.30046
[20] Vrahatis, A. G., Lazaros, K., & Kotsiantis, S. (2024). Graph attention networks: a comprehensive review of methods and applications. Future Internet, 16(9), 318. https://doi.org/10.3390/fi16090318
[21] Yu, X., Yang, S., Wang, Z., Song, S., Ma, H., Cao, Z., & Zhang, X. (2025, July). LIGHT: Enhancing Learning Path Recommendation via Knowledge Topology-Aware Sequence Optimization. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 306-315). https://doi.org/10.1145/3726302.3730022
[22] Amin, S., Uddin, M. I., Alarood, A. A., Mashwani, W. K., Alzahrani, A., & Alzahrani, A. O. (2023). Smart E-learning framework for personalized adaptive learning and sequential path recommendations using reinforcement learning. IEEe Access, 11, 89769-89790. https://doi.org/10.1109/access.2023.3305584
[23] Malashin, I., Tynchenko, V., Gantimurov, A., Nelyub, V., & Borodulin, A. (2024). Applications of long short-term memory (LSTM) networks in polymeric sciences: A review. Polymers, 16(18), 2607. https://doi.org/10.3390/polym16182607
[24] Xu, W., He, J., Li, W., He, Y., Wan, H., Qin, W., & Chen, Z. (2023). Long-short-term-memory-based deep stacked sequence-to-sequence autoencoder for health prediction of industrial workers in closed environments based on wearable devices. Sensors, 23(18), 7874. https://doi.org/10.3390/s23187874
[25] Jaramillo-Martínez, R., Chavero-Navarrete, E., & Ibarra-Pérez, T. (2024). Reinforcement-learning-based path planning: A reward function strategy. Applied Sciences, 14(17), 7654. https://doi.org/10.3390/app14177654
[26] Gallici, M., Fellows, M., Ellis, B., Pou, B., Masmitja, I., Foerster, J., & Martin, M. (2025, May). Simplifying deep temporal difference learning. In International Conference on Learning Representations (Vol. 2025, pp. 78148-78190). https://doi.org/10.48550/arXiv.2407.04811
[27] Hong, Z. W., Kumar, A., Karnik, S., Bhandwaldar, A., Srivastava, A., Pajarinen, J., ... & Agrawal, P. (2023). Beyond uniform sampling: Offline reinforcement learning with imbalanced datasets. Advances in Neural Information Processing Systems, 36, 4985-5009. https://doi.org/10.48550/arXiv.2310.04413
[28] Lockwood, O., & Si, M. (2022, October). A review of uncertainty for deep reinforcement learning. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (Vol. 18, No. 1, pp. 155-162). https://doi.org/10.1609/aiide.v18i1.21959
[29] Petravičius, T. (2023). Research and analysis of reinforcement learning methods in OpenAI Gym environment (Doctoral dissertation, Kauno technologijos universitetas.).
[30] Yadav, R. K. (2025). Modeling Memory Retention with Ebbinghaus's Forgetting Curve and Interpretable Machine Learning on Behavioral Factors. Authorea Preprints. https://doi.org/10.36227/techrxiv.174495325.58680708/v1
[31] De Melo, C. M., Torralba, A., Guibas, L., DiCarlo, J., Chellappa, R., & Hodgins, J. (2022). Next-generation deep learning based on simulators and synthetic data. Trends in cognitive sciences, 26(2), 174-187. https://doi.org/10.1016/j.tics.2021.11.008
[32] Ghorbani, Z., Mirebeigi-Jamasbi, S. S., Hassannia Dargah, M., Nahvi, M., Hosseinikhah Manshadi, S. A., & Akbarzadeh Fathabadi, Z. (2025). A novel deep learning-based model for automated tooth detection and numbering in mixed and permanent dentition in occlusal photographs. BMC Oral Health, 25(1), 455. https://doi.org/10.1186/s12903-025-05803-y
[33] Zhang, Z. (2026). Dynamic Pricing Strategy Optimization Based on a Reinforcement Learning PPO Algorithm: An Empirical Study on Ride-Hailing Platforms. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-43. https://doi.org/10.4018/JOEUC.406688
Published
Data Availability Statement
The data that support the findings of this study are available upon request from the corresponding authors, Y.L.
Issue
Section
License
Copyright (c) 2026 Sinuo Sun, Yansong Li (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
