Personalization for Web-based Services using Offline Reinforcement Learning
This work addresses the challenge of optimizing user interactions in large-scale web services for improved user experience, though it appears incremental as it applies existing offline RL methods to a new domain.
The paper tackled the problem of personalizing user interface policies for web-based services, specifically user authentication in a major social network, using offline reinforcement learning, resulting in significant improvements in long-term objectives.
Large-scale Web-based services present opportunities for improving UI policies based on observed user interactions. We address challenges of learning such policies through model-free offline Reinforcement Learning (RL) with off-policy training. Deployed in a production system for user authentication in a major social network, it significantly improves long-term objectives. We articulate practical challenges, compare several ML techniques, provide insights on training and evaluation of RL models, and discuss generalizations.