Outperformed by a Computer? - Comparing Human Decisions to Reinforcement Learning Agents, Assigning Lot Sizes in a Learning Factory: 11th Conference on Learning Factories, CLF2021

Publikation: Arbeits- oder Diskussionspapiere und BerichteArbeits- oder Diskussionspapiere

Standard

Harvard

APA

Vancouver

Bibtex

@techreport{f27161b0fb174f1ea53e8d1d76eb232d,
title = "Outperformed by a Computer? - Comparing Human Decisions to Reinforcement Learning Agents, Assigning Lot Sizes in a Learning Factory: 11th Conference on Learning Factories, CLF2021",
abstract = "Given the fact that some products in the production system require larger cycle times and a setup process during production, the application of different lot sizes might be beneficial regarding economic and logistic key performance indicators. Maximizing the profit considering the according work in process, inventory, set up and penalty costs is a complex challenge. In this contribution, we present the complete workflow from collecting data, deriving a simulation model, as well as training and deploying a machine learning model for assigning lot sizing in a dynamic production system. Furthermore, we compare the results of human participants and the reinforcement learning agent in a real-world learning factory workshop. The comparison of the results shows, that the reinforcement learning-agent is able to achieve the same level of results as the human experts. ",
keywords = "Engineering, reinforcement learning, Artifical intelligence, Lot sizing, Learning Factory",
author = "Thomas Vo{\ss} and Alexander Rokoss and Maier, {Janine Tatjana} and Matthias Schmidt and Jens Heger",
note = "11th Conference on Learning Factories; July 1st - July 2nd, 2021. Online Event. Posted: 4 Jun 2021",
year = "2021",
month = jun,
doi = "10.2139/ssrn.3859196",
language = "English",
series = "SSRN",
publisher = "Elsevier Inc.",
address = "United States",
type = "WorkingPaper",
institution = "Elsevier Inc.",

}

RIS

TY - UNPB

T1 - Outperformed by a Computer? - Comparing Human Decisions to Reinforcement Learning Agents, Assigning Lot Sizes in a Learning Factory

T2 - 11th Conference on Learning Factories, CLF2021

AU - Voß, Thomas

AU - Rokoss, Alexander

AU - Maier, Janine Tatjana

AU - Schmidt, Matthias

AU - Heger, Jens

N1 - 11th Conference on Learning Factories; July 1st - July 2nd, 2021. Online Event. Posted: 4 Jun 2021

PY - 2021/6

Y1 - 2021/6

N2 - Given the fact that some products in the production system require larger cycle times and a setup process during production, the application of different lot sizes might be beneficial regarding economic and logistic key performance indicators. Maximizing the profit considering the according work in process, inventory, set up and penalty costs is a complex challenge. In this contribution, we present the complete workflow from collecting data, deriving a simulation model, as well as training and deploying a machine learning model for assigning lot sizing in a dynamic production system. Furthermore, we compare the results of human participants and the reinforcement learning agent in a real-world learning factory workshop. The comparison of the results shows, that the reinforcement learning-agent is able to achieve the same level of results as the human experts.

AB - Given the fact that some products in the production system require larger cycle times and a setup process during production, the application of different lot sizes might be beneficial regarding economic and logistic key performance indicators. Maximizing the profit considering the according work in process, inventory, set up and penalty costs is a complex challenge. In this contribution, we present the complete workflow from collecting data, deriving a simulation model, as well as training and deploying a machine learning model for assigning lot sizing in a dynamic production system. Furthermore, we compare the results of human participants and the reinforcement learning agent in a real-world learning factory workshop. The comparison of the results shows, that the reinforcement learning-agent is able to achieve the same level of results as the human experts.

KW - Engineering

KW - reinforcement learning

KW - Artifical intelligence

KW - Lot sizing

KW - Learning Factory

UR - https://www.mendeley.com/catalogue/2d0008f5-c3eb-30da-8131-2d708cf3cad0/

U2 - 10.2139/ssrn.3859196

DO - 10.2139/ssrn.3859196

M3 - Working papers

T3 - SSRN

BT - Outperformed by a Computer? - Comparing Human Decisions to Reinforcement Learning Agents, Assigning Lot Sizes in a Learning Factory

PB - Elsevier Inc.

CY - Rochester

ER -