Since 2014
Programmatic Marketing via Reinforcement Learning
Journal of Business Management & Economics
View Archive Info| Field | Value | |
| Title |
Programmatic Marketing via Reinforcement Learning
|
|
| Creator |
Chen, Mengmeng; University of Central Florida Department of Industrial Engineering and Management Systems
Rabelo, Luis; University of Central Florida Department of Industrial Engineering and Management Systems |
|
| Description |
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.
|
|
| Publisher |
Journal of Business Management & Economics
|
|
| Contributor |
—
|
|
| Date |
2017-11-07
|
|
| Type |
info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion Peer-reviewed Article |
|
| Format |
application/pdf
|
|
| Identifier |
http://innovativejournal.in/jbme/index.php/jbme/article/view/269
10.15520/jbme.2017.vol5.iss11.269.pp01-04 |
|
| Source |
Journal of Business Management & Economics; Vol 5, No 11 (2017); 01-04
2347-5471 10.15520/jbme.2017.vol5.iss11 |
|
| Language |
eng
|
|
| Relation |
http://innovativejournal.in/jbme/index.php/jbme/article/view/269/pdf_146
10.15520/jbme.2017.vol5.iss11.269.319 |
|