An Exhaustive Analysis of Reinforcement Learning Implementations within Recommendation System Paradigms
DOI:
https://doi.org/10.54097/ac12v475Keywords:
Reinforcement Learning; Recommendation System; Deep Reinforcement Learning; Dynamic Environment; Multi-objective Optimization.Abstract
This manuscript begins with a detailed exploration of reinforcement learning, presenting a thorough analysis of its core models and algorithms. It contrasts these with traditional machine learning approaches, providing a nuanced comparative study. Following this, the paper dives into the origins and development of recommendation systems. It methodically classifies and explains the unique features of various prevalent recommendation algorithms. The focus of this research is the innovative integration of reinforcement learning in recommendation systems. It carefully examines how reinforcement learning can be merged with these systems, highlighting current challenges and outlining potential directions for future research, supported by empirical examples from practical applications. This comprehensive approach offers a deep insight into the interplay between advanced machine learning techniques and their application in improving recommendation systems. The manuscript aims to contribute significantly to the field by not only elucidating the theoretical underpinnings of these technologies but also by demonstrating their real-world efficacy and potential. Through this, it seeks to pave the way for more sophisticated, efficient, and personalized recommendation systems, driven by the latest advancements in machine learning.
Downloads
References
Yu, L., Du, Q., Yue, B., Xiang, J., Xv, G., & Leng, Y. (2021). Survey of Reinforcement Learning Based Recommender Systems. Computer Science, 48(10), 1-18.
Zhao, X., Zhang, L., Ding, Z., Xia, L., Tang, J., & Yin, D. (2018). Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning. arXiv preprint arXiv:1802.06501.
Zhao, X., Xia, L., Zhang, L., Ding, Z., Yin, D., & Tang, J. (2018). Deep Reinforcement Learning for Page-wise Recommendations. arXiv preprint arXiv:1805.02343.
Zheng, G., Zhang, F., Zheng, Z., Xiang, Y., Yuan, N. J., Xie, X., & Li, Z. (2018). DRN: A Deep Reinforcement Learning Framework for News Recommendation. In Proceedings of the World Wide Web Conference (WWW) (pp. 167-176).
Zhang, S., Yao, L., Sun, A., & Tay, Y. (2018). Deep Learning based Recommender System: A Survey and New Perspectives. ACM Computing Surveys, 1(1), Article 1, 35.
Zhou, P., Wang, K., Guo, L., Gong, S., & Zheng, B. (2021). A Privacy-Preserving Distributed Contextual Federated Online Learning Framework with Big Data Support in Social Recommender Systems. IEEE Transactions on Knowledge and Data Engineering, 33(3), 824-838. https://doi.org/10.1109/TKDE.2019.2936565
Xu, X., Xie, H., & Lui, J. C. S. (2023). Generalized Contextual Bandits With Latent Features: Algorithms and Applications. IEEE Transactions on Neural Networks and Learning Systems, 34(8), 4763-4775.
Afsar, M. M., Crump, T., & Far, B. (2018). Reinforcement Learning based Recommender Systems: A Survey. ACM Computing Surveys, 1(1), 37.
Neyshabouri, M. M., Gokcesu, K., Gokcesu, H., Ozkan, H., & Kozat, S. S. (2019). Asymptotically Optimal Contextual Bandit Algorithm Using Hierarchical Structures. IEEE Transactions on Neural Networks and Learning Systems, 30(3), 923-937.
Chen, S.-Y., Yu, Y., Da, Q., Tan, J., Huang, H.-K., & Tang, H.-H. (2018). Stabilizing Reinforcement Learning in Dynamic Environment with Application to Online Recommendation. In Proceedings of the SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 1187–1196).
Choi, S., Ha, H., Hwang, U., Kim, C., Ha, J.-W., & Yoon, S. (2018). Reinforcement Learning based Recommender System using Biclustering Technique. arXiv preprint arXiv:1801.05532.
Munemasa, I., Tomomatsu, Y., Hayashi, K., & Takagi, T. (2018). Deep Reinforcement Learning for Recommender Systems. (2018).
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
