Programmatic Marketing via Reinforcement Learning

  • Mengmeng Chen
  • Luis Rabelo
Cite this:
Chen, M., & Rabelo, L. (2017). Programmatic Marketing via Reinforcement Learning. Journal of Business Management and Economics, 5(11), 01–04. https://doi.org/10.15520/jbme.2017.vol5.iss11.269.pp01-04
© 2022 Interactive Protocols
RIGHTS & PERMISSIONS
Article Views
137
Altmetric
1
Citations
-
LEARN ABOUT THESE METRICS
   PDF  

Abstract

This new algorithm which incorporates look-ahead search inside the training loop resulting in rapid improvement and precise and stable learning. By using this new search methods towards programmatic marketing, we massively improve the return of investment on Google Adwords auction by 4.6% in 1 day. We apply simple, gradient-based updates to train the next policy and value network. This appears to be much more stable than incremental, gradient-based policy improvements such as policy gradient or Q-learning that can potentially forget previous improvements.

KEYWORDS:

 Special Issue

Article Metrics Graph

Chart Graph | Range Graph

Content

Section

Source