We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Discovering dispatching rules from data using imitation learning: A case study for the job-shop problem.
- Authors
Ingimundardottir, Helga; Runarsson, Thomas Philip
- Abstract
Dispatching rules can be automatically generated from scheduling data. This paper will demonstrate that the key to learning an effective dispatching rule is through the careful construction of the training data, {xi(k),yi(k)}k=1K∈D<inline-graphic></inline-graphic>, where (i) features of partially constructed schedules xi<inline-graphic></inline-graphic> should necessarily reflect the induced data distribution D<inline-graphic></inline-graphic> for when the rule is applied. This is achieved by updating the learned model in an active imitation learning fashion; (ii) yi<inline-graphic></inline-graphic> is labelled optimally using a MIP solver; and (iii) data need to be balanced, as the set is unbalanced with respect to the dispatching step k. Using the guidelines set by our framework the design of custom dispatching rules, for a particular scheduling application, will become more effective. In the study presented three different distributions of the job-shop will be considered. The machine learning approach considered is based on preference learning, i.e. which dispatch (post-decision state) is preferable to another.
- Subjects
SCHEDULING; DAGGERS; DATA distribution; IMITATIVE behavior; HEURISTIC
- Publication
Journal of Scheduling, 2018, Vol 21, Issue 4, p413
- ISSN
1094-6136
- Publication type
Article
- DOI
10.1007/s10951-017-0534-0