Self-adapting WIP parameter setting using deep reinforcement learning

DOI10.1016/J.COR.2022.105854MaRDI QIDQ2147128zbMATH OpenOpenAlexFDO

Authors Manuel Tomé De Andrade e. Silva, Américo Azevedo

Publication date 22 June 2022

Published in Computers \& Operations Research (Search for Journal in Brave)

Copyright license Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Full work available at URL https://doi.org/10.1016/j.cor.2022.105854

zbMATH Keywords

CONWIPdeep reinforcement learningWIP reduction

Mathematics Subject Classification ID

Operations research and management science (90Bxx)

Recommendations

• scientific article; zbMATH DE number 1958166
• Deep reinforcement learning for adaptive mesh refinement
• scientific article; zbMATH DE number 1738703
• Adaptive Q-learning
• Autonomous reinforcement learning with experience replay

Cites work

• A Mathematical Theory of Communication
• A dynamic programming model for the kanban assignment problem in a multistage multiperiod production system
• An adaptive approach to controlling kanban systems
• IMPALA
• Monotonicity of the Throughput of a Closed Queueing Network in the Number of Jobs
• Push and Pull Production Systems: Issues and Comparisons
• Reinforcement learning. An introduction
• Setting WIP levels with statistical throughput control (STC) in CONWIP production lines

Cited in

(2)

• Robustness evaluation of trust and reputation systems using a deep reinforcement learning approach
• Reward shaping to improve the performance of deep reinforcement learning in perishable inventory management

Describes a project that uses

Uses Software

• IMPALA

This page was built for publication: Self-adapting WIP parameter setting using deep reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2147128)