{"@context":{"@vocab":"https://cir.nii.ac.jp/schema/1.0/","rdfs":"http://www.w3.org/2000/01/rdf-schema#","dc":"http://purl.org/dc/elements/1.1/","dcterms":"http://purl.org/dc/terms/","foaf":"http://xmlns.com/foaf/0.1/","prism":"http://prismstandard.org/namespaces/basic/2.0/","cinii":"http://ci.nii.ac.jp/ns/1.0/","datacite":"https://schema.datacite.org/meta/kernel-4/","ndl":"http://ndl.go.jp/dcndl/terms/","jpcoar":"https://github.com/JPCOAR/schema/blob/master/2.0/"},"@id":"https://cir.nii.ac.jp/crid/1360588380140979200.json","@type":"Article","productIdentifier":[{"identifier":{"@type":"DOI","@value":"10.1007/s12065-024-00989-6"}},{"identifier":{"@type":"URI","@value":"https://link.springer.com/content/pdf/10.1007/s12065-024-00989-6.pdf"}},{"identifier":{"@type":"URI","@value":"https://link.springer.com/article/10.1007/s12065-024-00989-6/fulltext.html"}}],"resourceType":"学術雑誌論文(journal article)","dc:title":[{"@value":"Deep reinforcement learning-based spatio-temporal graph neural network for solving job shop scheduling problem"}],"description":[{"type":"abstract","notation":[{"@value":"<jats:title>Abstract</jats:title>\n          <jats:p>The job shop scheduling problem (JSSP) is a well-known NP-hard combinatorial optimization problem that focuses on assigning tasks to limited resources while adhering to certain constraints. Currently, deep reinforcement learning (DRL)-based solutions are being widely used to solve the JSSP by defining the problem structure on disjunctive graphs. Some of the proposed approaches attempt to leverage the structural information of the JSSP to capture the dynamics of the environment without considering the time dependency within the JSSP. However, learning graph representations only from the structural relationship of nodes results in a weak and incomplete representation of these graphs which does not provide an expressive representation of the dynamics in the environment. In this study, unlike existing frameworks, we defined the JSSP as a dynamic graph to explicitly consider the time-varying aspect of the JSSP environment. To this end, we propose a novel DRL framework that captures both the spatial and temporal attributes of the JSSP to construct rich and complete graph representations. Our DRL framework introduces a novel attentive graph isomorphism network (Attentive-GIN)-based spatial block to learn the structural relationship and a temporal block to capture the time dependency. Additionally, we designed a gated fusion block that selectively combines the learned representations from the two blocks. We trained the model using the proximal policy optimization algorithm of reinforcement learning. Experimental results show that our trained model exhibits significant performance enhancement compared to heuristic dispatching rules and learning-based solutions for both randomly generated datasets and public benchmarks.</jats:p>"}]}],"creator":[{"@id":"https://cir.nii.ac.jp/crid/1380588380140979353","@type":"Researcher","foaf:name":[{"@value":"Goytom Gebreyesus"}]},{"@id":"https://cir.nii.ac.jp/crid/1380588380140979344","@type":"Researcher","foaf:name":[{"@value":"Getu Fellek"}]},{"@id":"https://cir.nii.ac.jp/crid/1380588380140979350","@type":"Researcher","foaf:name":[{"@value":"Ahmed Farid"}]},{"@id":"https://cir.nii.ac.jp/crid/1380588380140979357","@type":"Researcher","foaf:name":[{"@value":"Sicheng Hou"}]},{"@id":"https://cir.nii.ac.jp/crid/1380588380140979354","@type":"Researcher","foaf:name":[{"@value":"Shigeru Fujimura"}]},{"@id":"https://cir.nii.ac.jp/crid/1380588380140979333","@type":"Researcher","foaf:name":[{"@value":"Osamu Yoshie"}]}],"publication":{"publicationIdentifier":[{"@type":"PISSN","@value":"18645909"},{"@type":"EISSN","@value":"18645917"}],"prism:publicationName":[{"@value":"Evolutionary Intelligence"}],"dc:publisher":[{"@value":"Springer Science and Business Media LLC"}],"prism:publicationDate":"2024-11-16","prism:volume":"18","prism:number":"1"},"reviewed":"false","dc:rights":["https://creativecommons.org/licenses/by/4.0","https://creativecommons.org/licenses/by/4.0"],"url":[{"@id":"https://link.springer.com/content/pdf/10.1007/s12065-024-00989-6.pdf"},{"@id":"https://link.springer.com/article/10.1007/s12065-024-00989-6/fulltext.html"}],"createdAt":"2024-11-16","modifiedAt":"2025-02-21","project":[{"@id":"https://cir.nii.ac.jp/crid/1040577277048725632","@type":"Project","projectIdentifier":[{"@type":"KAKEN","@value":"23K04278"},{"@type":"JGN","@value":"JP23K04278"},{"@type":"URI","@value":"https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-23K04278/"}],"notation":[{"@language":"ja","@value":"自動走行搬送ロボット・作業者協調作業のためのリアクティブ・スケジューリング"}]}],"relatedProduct":[{"@id":"https://cir.nii.ac.jp/crid/1360016870035029632","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Reinforcement learning applications to machine scheduling problems: a comprehensive literature review"}]},{"@id":"https://cir.nii.ac.jp/crid/1360021389819200000","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Gated‐Attention Model with Reinforcement Learning for Solving Dynamic Job Shop Scheduling Problem"}]},{"@id":"https://cir.nii.ac.jp/crid/1360025435022279808","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A Deep Reinforcement Learning Based Solution for Flexible Job Shop Scheduling Problem"}]},{"@id":"https://cir.nii.ac.jp/crid/1360025438507086720","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"UCRLF: unified constrained reinforcement learning framework for phase-aware architectures for autonomous vehicle signaling and trajectory optimization"}]},{"@id":"https://cir.nii.ac.jp/crid/1360025438507087616","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"ORAD: a new framework of offline Reinforcement Learning with Q-value regularization"}]},{"@id":"https://cir.nii.ac.jp/crid/1360025438507319424","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Job Shop Scheduling: A Novel DRL approach for continuous schedule-generation facing real-time job arrivals"}]},{"@id":"https://cir.nii.ac.jp/crid/1360025438508347904","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Dynamic graph combinatorial optimization with multi-attention deep reinforcement learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360025439015664128","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Deep attention models with dimension-reduction and gate mechanisms for solving practical time-dependent vehicle routing problems"}]},{"@id":"https://cir.nii.ac.jp/crid/1360025439154861184","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Multi-agent systems negotiation to deal with dynamic scheduling in disturbed industrial context"}]},{"@id":"https://cir.nii.ac.jp/crid/1360025439394256000","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"An End-to-End Deep Reinforcement Learning Approach for Job Shop Scheduling"}]},{"@id":"https://cir.nii.ac.jp/crid/1360298340866933888","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Job shop scheduling"}]},{"@id":"https://cir.nii.ac.jp/crid/1360302870129921536","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A Deep Reinforcement Learning Framework Based on an Attention Mechanism and Disjunctive Graph Embedding for the Job-Shop Scheduling Problem"}]},{"@id":"https://cir.nii.ac.jp/crid/1360302870446228352","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Dynamic scheduling in a job-shop production system with reinforcement learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360302870447044352","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Intelligent Scheduling with Reinforcement Learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360306908999113728","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Semisupervised Defect Segmentation With Pairwise Similarity Map Consistency and Ensemble-Based Cross Pseudolabels"}]},{"@id":"https://cir.nii.ac.jp/crid/1360306911442110080","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Migrating Birds Optimization: A new metaheuristic approach and its performance on quadratic assignment problem"}]},{"@id":"https://cir.nii.ac.jp/crid/1360306912224407424","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Optimization of job shop scheduling problem based on deep reinforcement learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360306912224616576","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Day-ahead multi-modal demand side management in microgrid via two-stage improved ring-topology particle swarm optimization"}]},{"@id":"https://cir.nii.ac.jp/crid/1360306913358033536","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Using Attention Mechanism to Solve Job Shop Scheduling Problem"}]},{"@id":"https://cir.nii.ac.jp/crid/1360306913996778496","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Genetic algorithm applications on Job Shop Scheduling Problem: A review"}]},{"@id":"https://cir.nii.ac.jp/crid/1360576122142040064","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Temporal Multi-Graph Convolutional Network for Traffic Flow Prediction"}]},{"@id":"https://cir.nii.ac.jp/crid/1360579927779290752","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A Review of Dynamic Job Shop Scheduling Techniques"}]},{"@id":"https://cir.nii.ac.jp/crid/1360584346089993216","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"An integer linear‐programming model for machine scheduling"}]},{"@id":"https://cir.nii.ac.jp/crid/1360584346090947328","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Learning to schedule job-shop problems: representation and policy learning using graph neural network and reinforcement learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360584346091076224","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Research on Adaptive Job Shop Scheduling Problems Based on Dueling Double DQN"}]},{"@id":"https://cir.nii.ac.jp/crid/1360588385571937280","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Modified Migrating Birds Optimization for Energy-Aware Flexible Job Shop Scheduling Problem"}]},{"@id":"https://cir.nii.ac.jp/crid/1360588386232944384","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Dynamic Scheduling Method for Job-Shop Manufacturing Systems by Deep Reinforcement Learning with Proximal Policy Optimization"}]},{"@id":"https://cir.nii.ac.jp/crid/1360588387545582208","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Dynamic parallel machine scheduling with mean weighted tardiness objective by Q-Learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360588388703821824","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"An improved migrating birds optimization for an integrated lot-streaming flow shop scheduling problem"}]},{"@id":"https://cir.nii.ac.jp/crid/1360588389241748352","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Dynamic Jobshop Scheduling Algorithm Based on Deep Q Network"}]},{"@id":"https://cir.nii.ac.jp/crid/1360588389345725696","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Flexible Job-Shop Scheduling via Graph Neural Network and Deep Reinforcement Learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360853567794625920","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Distributed-elite local search based on a genetic algorithm for bi-objective job-shop scheduling under time-of-use tariffs"}]},{"@id":"https://cir.nii.ac.jp/crid/1360865818714049664","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A reinforcement learning approach to parameter estimation in dynamic job shop scheduling"}]},{"@id":"https://cir.nii.ac.jp/crid/1360865818714760960","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A Hybrid Particle-Swarm Tabu Search Algorithm for Solving Job Shop Scheduling Problems"}]},{"@id":"https://cir.nii.ac.jp/crid/1360865819391626496","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Reinforcement Learning With Multiple Relational Attention for Solving Vehicle Routing Problems"}]},{"@id":"https://cir.nii.ac.jp/crid/1360869862648812160","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Graph Transformer with Reinforcement Learning for Vehicle Routing Problem"}]},{"@id":"https://cir.nii.ac.jp/crid/1360869862649061120","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A new asynchronous reinforcement learning algorithm based on improved parallel PSO"}]},{"@id":"https://cir.nii.ac.jp/crid/1360869862650074496","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Solving Time-Dependent Traveling Salesman Problem with Time Windows with Deep Reinforcement Learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1361418519087494784","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Applications of asynchronous deep reinforcement learning based on dynamic updating weights"}]},{"@id":"https://cir.nii.ac.jp/crid/1361699993508175744","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A comparison of priority rules for the job shop scheduling problem under different flow time- and tardiness-related objective functions"}]},{"@id":"https://cir.nii.ac.jp/crid/1361699993923828608","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Benchmarks for basic scheduling problems"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544418577181312","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Adaptation in Natural and Artificial Systems"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544419852505216","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Deterministic job-shop scheduling: Past, present and future"}]},{"@id":"https://cir.nii.ac.jp/crid/1363388843215756416","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Human-level control through deep reinforcement learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951793749656576","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Benchmarks for shop scheduling problems"}]}],"dataSourceIdentifier":[{"@type":"CROSSREF","@value":"10.1007/s12065-024-00989-6"},{"@type":"KAKEN","@value":"PRODUCT-25712266"}]}