Waubert de Puiseau, C.; Tercan, H.; Meisen, T.: Curriculum Learning in Job Shop Scheduling using Reinforcement Learning. In: Herberger, D.; Hübner, M.; Stich, V. (Eds.): Proceedings of the Conference on Production Systems and Logistics: CPSL 2023 - 1. Hannover : publish-Ing., 2023, S. 34-43. DOI: https://doi.org/10.15488/13422
Zusammenfassung: | |
Solving job shop scheduling problems (JSSPs) with a fixed strategy, such as a priority dispatching rule, may yield satisfactory results for several problem instances but, nevertheless, insufficient results for others. From this single-strategy perspective finding a near optimal solution to a specific JSSP varies in difficulty even if the machine setup remains the same. A recent intensively researched and promising method to deal with difficulty variability is Deep Reinforcement Learning (DRL), which dynamically adjusts an agent's planning strategy in response to difficult instances not only during training, but also when applied to new situations. In this paper, we further improve DLR as an underlying method by actively incorporating the variability of difficulty within the same problem size into the design of the learning process. We base our approach on a state-of-the-art methodology that solves JSSP by means of DRL and graph neural network embeddings. Our work supplements the training routine of the agent by a curriculum learning strategy that ranks the problem instances shown during training by a new metric of problem instance difficulty. Our results show that certain curricula lead to significantly better performances of the DRL solutions. Agents trained on these curricula beat the top performance of those trained on randomly distributed training data, reaching 3.2% shorter average makespans. | |
Lizenzbestimmungen: | CC BY 3.0 DE |
Publikationstyp: | BookPart |
Publikationsstatus: | publishedVersion |
Erstveröffentlichung: | 2023 |
Die Publikation erscheint in Sammlung(en): | Proceedings CPSL 2023 - 1 Proceedings CPSL 2023 - 1 |
Pos. | Land | Downloads | ||
---|---|---|---|---|
Anzahl | Proz. | |||
1 | Germany | 129 | 57,59% | |
2 | Netherlands | 21 | 9,37% | |
3 | United States | 18 | 8,04% | |
4 | China | 11 | 4,91% | |
5 | No geo information available | 8 | 3,57% | |
6 | Poland | 6 | 2,68% | |
7 | Iran, Islamic Republic of | 3 | 1,34% | |
8 | Israel | 3 | 1,34% | |
9 | France | 3 | 1,34% | |
10 | Switzerland | 3 | 1,34% | |
andere | 19 | 8,48% |
Hinweis
Zur Erhebung der Downloadstatistiken kommen entsprechend dem „COUNTER Code of Practice for e-Resources“ international anerkannte Regeln und Normen zur Anwendung. COUNTER ist eine internationale Non-Profit-Organisation, in der Bibliotheksverbände, Datenbankanbieter und Verlage gemeinsam an Standards zur Erhebung, Speicherung und Verarbeitung von Nutzungsdaten elektronischer Ressourcen arbeiten, welche so Objektivität und Vergleichbarkeit gewährleisten sollen. Es werden hierbei ausschließlich Zugriffe auf die entsprechenden Volltexte ausgewertet, keine Aufrufe der Website an sich.