MétaCan
Menu
Back to cohort
Record W4416530376 · doi:10.1080/21693277.2025.2582472

Reinforcement learning based dispatching solutions in semiconductor manufacturing: a literature review on validation and deployment

2025· article· en· W4416530376 on OpenAlex
Patrick Stöckermann, Sebastian Feudel, Alessandro Immordino, Niels Hayen, Thomas Altenmüller, Martin Gebser, Konstantin Schekotihin, Georg Seidel, Marc Wegmann, Fin Higgins

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueProduction & Manufacturing Research · 2025
Typearticle
Languageen
FieldEngineering
TopicScheduling and Optimization Algorithms
Canadian institutionsInfineon Technologies (Canada)
FundersÖsterreichische ForschungsförderungsgesellschaftBundesministerium für Wirtschaft und Klimaschutz
KeywordsSoftware deploymentScheduling (production processes)Wafer fabricationKey (lock)Semiconductor device fabricationPipeline (software)

Abstract

fetched live from OpenAlex

AI-based scheduling methods have been shown to be highly effective in increasing the overall efficiency of production facilities such as semiconductor wafer fabrication in academic works. Especially RL has been demonstrated to be a powerful tool for global optimization. However, the public body of knowledge lacks validation and deployment approaches as well as guidelines for implementation in real fabrication facilities. We conduct a structured literature review to identify the key challenges regarding validation and deployment that are mentioned in literature. Next, we provide a summary of these challenges and introduce solution methods, as well as guidelines for implementation. As a practical example, we propose a Machine Learning pipeline for continuous deployment, as well as an architecture that combines classical dispatching and scheduling methods with RL.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.758
Threshold uncertainty score0.808

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.037
GPT teacher head0.314
Teacher spread0.277 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it