Personalization for Web-Based Services Using Offline Reinforcement Learning

Pavlos Athanasios Apostolopoulos, Zehui Wang, Hanson Wang, Tenghyu Xu, Chad Zhou, Kittipat Virochsiri, Norm Zhou, Igor L. Markov

MLJ 2024 pp. 3049-3071

doi:10.1007/S10994-024-06525-Y /mlj/2024/apostolopoulos2024mlj-personalization/

Abstract

Large-scale Web-based services present opportunities for improving UI policies based on observed user interactions. We address challenges of learning such policies through offline reinforcement learning (RL). Deployed in a production system for user authentication in a major social network, it significantly improves long-term objectives. We articulate practical challenges, provide insights on training and evaluation of offline RL, and discuss generalizations toward offline RL’s deployment in industry-scale applications.

PDF MLJ Semantic Scholar

Cite

Text

Apostolopoulos et al. "Personalization for Web-Based Services Using Offline Reinforcement Learning." Machine Learning, 2024. doi:10.1007/S10994-024-06525-Y

Markdown

[Apostolopoulos et al. "Personalization for Web-Based Services Using Offline Reinforcement Learning." Machine Learning, 2024.](https://mlanthology.org/mlj/2024/apostolopoulos2024mlj-personalization/) doi:10.1007/S10994-024-06525-Y

BibTeX

@article{apostolopoulos2024mlj-personalization,
  title     = {{Personalization for Web-Based Services Using Offline Reinforcement Learning}},
  author    = {Apostolopoulos, Pavlos Athanasios and Wang, Zehui and Wang, Hanson and Xu, Tenghyu and Zhou, Chad and Virochsiri, Kittipat and Zhou, Norm and Markov, Igor L.},
  journal   = {Machine Learning},
  year      = {2024},
  pages     = {3049-3071},
  doi       = {10.1007/S10994-024-06525-Y},
  volume    = {113},
  url       = {https://mlanthology.org/mlj/2024/apostolopoulos2024mlj-personalization/}
}