Combining deep reinforcement learning and meta-heuristic techniques represents a new research direction for enhancing the search capabilities of meta-heuristic methods in the context of production scheduling. Q-learning is a prominent reinforcement learning in which its utilization aims to direct the selection of actions, thus preventing the necessity for a random exploration in the iterative process of the metaheuristics. In this study, we provide Q-learning guided algorithms for the Bi-Criteria No-Wait Flowshop Scheduling Problem (NWFSP). The problem is treated as a bi-criteria combinatorial optimization problem where total flow time and makespan are optimized simultaneously. Firstly, a deterministic mixed-integer linear programming model is provided. Then, Q-learning guided algorithms are developed: Bi-Criteria Iterated Greedy Algorithm with Q-learning and Bi-Criteria Block Insertion Heuristic Algorithm with Q-learning. Moreover, the performance of the proposed Q-learning-guided algorithms is compared over a collection of heuristics in the literature. The complete computational experiment, that is performed on the 480 problem instances known as the VRF benchmark set, indicates that the proposed Q-learning guided algorithms can yield more non-dominated bi-criteria solutions with the most substantial competitiveness than the remaining algorithms. At the same time, both are competitive with each other on the benchmark problems. Among all the features that have been compared, the Q-learning-guided algorithms demonstrate the highest level of competitiveness. The outcomes of this study encourage us to discover (i) the effectiveness of the Q-learning integration into metaheuristics applied for the flowshop scheduling problems, and (ii) many more bi-criteria NWFSPs for revealing the trade-offs between other conflicting objectives, such as makespan & the number of tardy jobs, to overcome various industries' problems.
Damla Yuksel: Q-learning Guided Algorithms in Flowshops 5 December 2024 16:00 - 17:00
About Damla Yuksel: Q-learning Guided Algorithms in Flowshops
Starting date
- 5 December 2024
Time
- 16:00 - 17:00
Location
- VU Main Building
Address
- De Boelelaan 1105
- 1081 HV Amsterdam
Organised by
- Operations Analytics
Language
- English
Damla Yuksel
Damla Yuksel obtained her B.Sc. in Industrial Systems Engineering and completed a Double Major Program in International Trade and Finance at Izmir University of Economics, Turkey in 2016. She studied at Maynooth University, Ireland as an exchange student within the scope of the Erasmus + Student Exchange Program. After receiving her M.Sc. in Industrial Engineering from Yaşar University in 2019, she pursued her Ph.D. in the same department, which she completed in August 2024. Her thesis study focused on flowshop scheduling problems and involved developing mathematical models (mixed-integer linear programming and constraint programming models), along with valid inequalities, lower bounding and upper bounding heuristics, metaheuristics, due date generation mechanisms, and bi-objective optimization for No-Wait Permutation Flowshop Scheduling Problems. She worked as a Research Assistant for five years in the Industrial Engineering department at Yaşar University. Her research interests include scheduling problems, green/energy-efficient scheduling, mathematical modeling, multi-objective optimization, supply chain network designs, food supply chains, and sustainability and circularity in supply chains.
Interested in attending the seminar or in giving a talk?
Please send an email to Tim Oosterwijk