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 proceedingConference paperResearch

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 languageEnglish
Title of host publicationOptimization and Learning - Third International Conference, OLA2020, Cádiz, Spain, February 17-19, 2020, Proceedings
EditorsBernabé Dorronsoro, Patricia Ruiz, Juan Carlos de la Torre, Daniel Urda, El-Ghazali Talbi
PublisherSpringer
Pages3-12
Number of pages10
Volume1173
DOIs
Publication statusPublished - 2020
EventThe International Conference in Optimization and Learning - , Spain
Duration: 17 Feb 202019 Feb 2020
https://ola2020.sciencesconf.org/

Publication series

NameCommunications in Computer and Information Science
PublisherSpringer

Conference

ConferenceThe International Conference in Optimization and Learning
Abbreviated titleOLA2020
Country/TerritorySpain
Period17/02/2019/02/20
Internet address

Fingerprint

Dive into the research topics of 'Multi-Agent Reinforcement Learning Tool for Job Shop Scheduling Problems'. Together they form a unique fingerprint.

Cite this