Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
387247 | Expert Systems with Applications | 2009 | 10 Pages |
Abstract
In this work, RL is used to find an optimal policy for a marketing campaign. Data show a complex characterization of state and action spaces. Two approaches are proposed to circumvent this problem. The first approach is based on the self-organizing map (SOM), which is used to aggregate states. The second approach uses a multilayer perceptron (MLP) to carry out a regression of the action-value function. The results indicate that both approaches can improve a targeted marketing campaign. Moreover, the SOM approach allows an intuitive interpretation of the results, and the MLP approach yields robust results with generalization capabilities.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Gabriel Gómez-Pérez, José D. Martín-Guerrero, Emilio Soria-Olivas, Emili Balaguer-Ballester, Alberto Palomares, Nicolás Casariego,