LGHCSEFeb 10, 2021

Personalization for Web-based Services using Offline Reinforcement Learning

arXiv:2102.05612v17 citations
Originality Synthesis-oriented
AI Analysis

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes