Reinforcement Learning for Personalization

This page displays data on papers that use reinforcement learning for personalization problems. The data papers were collected on June 6, 2018 and analyzed following a systematic literature approach to provide a comprehensive overview.

This tool accompanies a paper that can be accessed here.

Usage

Various metrics can be displayed using the "Plot" dropdown (x-axis) and grouped using the "Group by" dropdown. As an example, plot "Domain" and group by "Is training performed on a simulator" to get an overview of usage of simulators in various application domains.

Entries can be filtered by year and domain using the timeline and checkboxes underneath the plot. Undo and redo buttons can be found in the bottom left. An export of the selection can be made using the "Download" button.