Intelligent Inventory Control: Is Bootstrapping Worth Implementing? - Intelligent Information Processing VI
Conference Papers Year : 2012

Intelligent Inventory Control: Is Bootstrapping Worth Implementing?

Abstract

The common belief is that using Reinforcement Learning methods (RL) with bootstrapping gives better results than without. However, inclusion of bootstrapping increases the complexity of the RL implementation and requires significant effort. This study investigates whether inclusion of bootstrapping is worth the effort when applying RL to inventory problems. Specifically, we investigate bootstrapping of the temporal difference learning method by using eligibility trace. In addition, we develop a new bootstrapping extension to the Residual Gradient method to supplement our investigation. The results show questionable benefit of bootstrapping when applied to inventory problems. Significance tests could not confirm that bootstrapping had statistically significantly reduced costs of inventory controlled by a RL agent. Our empirical results are based on a variety of problem settings, including demand correlations, demand variances, and cost structures.
Fichier principal
Vignette du fichier
978-3-642-32891-6_10_Chapter.pdf (250 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01524959 , version 1 (19-05-2017)

Licence

Identifiers

Cite

Tatpong Katanyukul, Edwin Chong, William S. Duff. Intelligent Inventory Control: Is Bootstrapping Worth Implementing?. 7th International Conference on Intelligent Information Processing (IIP), Oct 2012, Guilin, China. pp.58-67, ⟨10.1007/978-3-642-32891-6_10⟩. ⟨hal-01524959⟩
129 View
101 Download

Altmetric

Share

More