%0 Conference Proceedings
%T Intelligent Inventory Control: Is Bootstrapping Worth Implementing?
%+ Faculty of Engineering [Khon Kaen University]
%+ Department of Computer Science [Colorado State University]
%+ Department of Electrical and Computer Engineering [Fort Collins]
%A Katanyukul, Tatpong
%A Chong, Edwin
%A Duff, William, S.
%Z Part 3: Data Mining
%< avec comité de lecture
%( IFIP Advances in Information and Communication Technology
%B 7th International Conference on Intelligent Information Processing (IIP)
%C Guilin, China
%Y Zhongzhi Shi
%Y David Leake
%Y Sunil Vadera
%I Springer
%3 Intelligent Information Processing VI
%V AICT-385
%P 58-67
%8 2012-10-12
%D 2012
%R 10.1007/978-3-642-32891-6_10
%K approximate dynamic programming
%K inventory control
%K reinforcement learning
%K bootstrapping
%K eligibility trace
%K intelligent agent
%Z Computer Science [cs]Conference papers
%X 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.
%G English
%Z TC 12
%2 https://inria.hal.science/hal-01524959/document
%2 https://inria.hal.science/hal-01524959/file/978-3-642-32891-6_10_Chapter.pdf
%L hal-01524959
%U https://inria.hal.science/hal-01524959
%~ IFIP
%~ IFIP-AICT
%~ IFIP-TC
%~ IFIP-TC12
%~ IFIP-IIP
%~ IFIP-AICT-385