Multi-Agent Reinforcement Learning Tool for Job Shop Scheduling Problems

Yailen Martínez Jiménez; Jessica Coto Palacio; Ann Nowé

doi:10.1007/978-3-030-41913-41

Multi-Agent Reinforcement Learning Tool for Job Shop Scheduling Problems

Yailen Martínez Jiménez, Jessica Coto Palacio, Ann Nowé

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › Research

Abstract

The emergence of Industry 4.0 allows for new approaches to solve industrial problems such as the Job Shop Scheduling Problem. It has been demonstrated that Multi-Agent Reinforcement Learning approaches are highly promising to handle complex scheduling scenarios. In this work we propose a user friendly Multi-Agent Reinforcement Learning tool, more appealing for industry. It allows the users to interact with the learning algorithms in such a way that all the constraints in the production floor are carefully included and the objectives can be adapted to real world scenarios. The user can either keep the best schedule obtained by a Q-Learning algorithm or adjust it by fixing some operations in order to meet certain constraints, then the tool will optimize the modified solution respecting the user preferences using two possible alternatives. These alternatives are validated using OR-Library benchmarks, the experiments show that the modified Q-Learning algorithm is able to obtain the best results.

Original language	English
Title of host publication	Optimization and Learning - Third International Conference, OLA2020, Cádiz, Spain, February 17-19, 2020, Proceedings
Editors	Bernabé Dorronsoro, Patricia Ruiz, Juan Carlos de la Torre, Daniel Urda, El-Ghazali Talbi
Publisher	Springer
Pages	3-12
Number of pages	10
Volume	1173
DOIs	https://doi.org/10.1007/978-3-030-41913-41
Publication status	Published - 2020
Event	The International Conference in Optimization and Learning - , Spain Duration: 17 Feb 2020 → 19 Feb 2020 https://ola2020.sciencesconf.org/

Publication series

Name	Communications in Computer and Information Science
Publisher	Springer

Conference

Conference	The International Conference in Optimization and Learning
Abbreviated title	OLA2020
Country/Territory	Spain
Period	17/02/20 → 19/02/20
Internet address	https://ola2020.sciencesconf.org/

Access to Document

10.1007/978-3-030-41913-41

https://doi.org/10.1007/978-3-030-41913-41

Cite this

Jiménez, Y. M., Palacio, J. C., & Nowé, A. (2020). Multi-Agent Reinforcement Learning Tool for Job Shop Scheduling Problems. In B. Dorronsoro, P. Ruiz, J. C. D. L. Torre, D. Urda, & E-G. Talbi (Eds.), Optimization and Learning - Third International Conference, OLA2020, Cádiz, Spain, February 17-19, 2020, Proceedings (Vol. 1173, pp. 3-12). (Communications in Computer and Information Science). Springer. https://doi.org/10.1007/978-3-030-41913-41

Jiménez, Yailen Martínez ; Palacio, Jessica Coto ; Nowé, Ann. / Multi-Agent Reinforcement Learning Tool for Job Shop Scheduling Problems. Optimization and Learning - Third International Conference, OLA2020, Cádiz, Spain, February 17-19, 2020, Proceedings. editor / Bernabé Dorronsoro ; Patricia Ruiz ; Juan Carlos de la Torre ; Daniel Urda ; El-Ghazali Talbi. Vol. 1173 Springer, 2020. pp. 3-12 (Communications in Computer and Information Science).

@inproceedings{9ac6c01aca7e46c5ae7f1eb29930f85b,

title = "Multi-Agent Reinforcement Learning Tool for Job Shop Scheduling Problems",

abstract = "The emergence of Industry 4.0 allows for new approaches to solve industrial problems such as the Job Shop Scheduling Problem. It has been demonstrated that Multi-Agent Reinforcement Learning approaches are highly promising to handle complex scheduling scenarios. In this work we propose a user friendly Multi-Agent Reinforcement Learning tool, more appealing for industry. It allows the users to interact with the learning algorithms in such a way that all the constraints in the production floor are carefully included and the objectives can be adapted to real world scenarios. The user can either keep the best schedule obtained by a Q-Learning algorithm or adjust it by fixing some operations in order to meet certain constraints, then the tool will optimize the modified solution respecting the user preferences using two possible alternatives. These alternatives are validated using OR-Library benchmarks, the experiments show that the modified Q-Learning algorithm is able to obtain the best results.",

author = "Jim{\'e}nez, {Yailen Mart{\'i}nez} and Palacio, {Jessica Coto} and Ann Now{\'e}",

year = "2020",

doi = "10.1007/978-3-030-41913-41",

language = "English",

volume = "1173",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "3--12",

editor = "Bernab{\'e} Dorronsoro and Patricia Ruiz and Torre, {Juan Carlos de la} and Daniel Urda and El-Ghazali Talbi",

booktitle = "Optimization and Learning - Third International Conference, OLA2020, C{\'a}diz, Spain, February 17-19, 2020, Proceedings",

note = "The International Conference in Optimization and Learning, OLA2020 ; Conference date: 17-02-2020 Through 19-02-2020",

url = "https://ola2020.sciencesconf.org/",

}

Jiménez, YM, Palacio, JC & Nowé, A 2020, Multi-Agent Reinforcement Learning Tool for Job Shop Scheduling Problems. in B Dorronsoro, P Ruiz, JCDL Torre, D Urda & E-G Talbi (eds), Optimization and Learning - Third International Conference, OLA2020, Cádiz, Spain, February 17-19, 2020, Proceedings. vol. 1173, Communications in Computer and Information Science, Springer, pp. 3-12, The International Conference in Optimization and Learning, Spain, 17/02/20. https://doi.org/10.1007/978-3-030-41913-41

Multi-Agent Reinforcement Learning Tool for Job Shop Scheduling Problems. / Jiménez, Yailen Martínez; Palacio, Jessica Coto; Nowé, Ann.

Optimization and Learning - Third International Conference, OLA2020, Cádiz, Spain, February 17-19, 2020, Proceedings. ed. / Bernabé Dorronsoro; Patricia Ruiz; Juan Carlos de la Torre; Daniel Urda; El-Ghazali Talbi. Vol. 1173 Springer, 2020. p. 3-12 (Communications in Computer and Information Science).

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › Research

TY - GEN

T1 - Multi-Agent Reinforcement Learning Tool for Job Shop Scheduling Problems

AU - Jiménez, Yailen Martínez

AU - Palacio, Jessica Coto

AU - Nowé, Ann

PY - 2020

Y1 - 2020

N2 - The emergence of Industry 4.0 allows for new approaches to solve industrial problems such as the Job Shop Scheduling Problem. It has been demonstrated that Multi-Agent Reinforcement Learning approaches are highly promising to handle complex scheduling scenarios. In this work we propose a user friendly Multi-Agent Reinforcement Learning tool, more appealing for industry. It allows the users to interact with the learning algorithms in such a way that all the constraints in the production floor are carefully included and the objectives can be adapted to real world scenarios. The user can either keep the best schedule obtained by a Q-Learning algorithm or adjust it by fixing some operations in order to meet certain constraints, then the tool will optimize the modified solution respecting the user preferences using two possible alternatives. These alternatives are validated using OR-Library benchmarks, the experiments show that the modified Q-Learning algorithm is able to obtain the best results.

AB - The emergence of Industry 4.0 allows for new approaches to solve industrial problems such as the Job Shop Scheduling Problem. It has been demonstrated that Multi-Agent Reinforcement Learning approaches are highly promising to handle complex scheduling scenarios. In this work we propose a user friendly Multi-Agent Reinforcement Learning tool, more appealing for industry. It allows the users to interact with the learning algorithms in such a way that all the constraints in the production floor are carefully included and the objectives can be adapted to real world scenarios. The user can either keep the best schedule obtained by a Q-Learning algorithm or adjust it by fixing some operations in order to meet certain constraints, then the tool will optimize the modified solution respecting the user preferences using two possible alternatives. These alternatives are validated using OR-Library benchmarks, the experiments show that the modified Q-Learning algorithm is able to obtain the best results.

U2 - 10.1007/978-3-030-41913-41

DO - 10.1007/978-3-030-41913-41

M3 - Conference paper

VL - 1173

T3 - Communications in Computer and Information Science

SP - 3

EP - 12

BT - Optimization and Learning - Third International Conference, OLA2020, Cádiz, Spain, February 17-19, 2020, Proceedings

A2 - Dorronsoro, Bernabé

A2 - Ruiz, Patricia

A2 - Torre, Juan Carlos de la

A2 - Urda, Daniel

A2 - Talbi, El-Ghazali

PB - Springer

T2 - The International Conference in Optimization and Learning

Y2 - 17 February 2020 through 19 February 2020

ER -

Jiménez YM, Palacio JC, Nowé A. Multi-Agent Reinforcement Learning Tool for Job Shop Scheduling Problems. In Dorronsoro B, Ruiz P, Torre JCDL, Urda D, Talbi E-G, editors, Optimization and Learning - Third International Conference, OLA2020, Cádiz, Spain, February 17-19, 2020, Proceedings. Vol. 1173. Springer. 2020. p. 3-12. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-030-41913-41

Multi-Agent Reinforcement Learning Tool for Job Shop Scheduling Problems

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this