loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Christoph Schmidl 1 ; Thiago Simão 2 and Nils Jansen 1 ; 3

Affiliations: 1 Radboud University, Nijmegen, The Netherlands ; 2 Eindhoven University of Technology, The Netherlands ; 3 Ruhr-University Bochum, Germany

Keyword(s): Reinforcement Learning, Job-Shop, Scheduling, Operations Research, Permutation, Robustness.

Abstract: The job shop scheduling problem (JSSP) is an NP-hard combinatorial optimization problem with the objective of minimizing the makespan while adhering to domain-specific constraints. Recent developments cast JSSP as a reinforcement learning (RL) problem, diverging from classical methods like heuristics or constraint programming. However, RL policies, serving as schedulers, often lack permutation invariance for job orderings in JSSP, limiting their generalization capabilities. In this paper, we improve the generalization of RL in the JSSP using a three-step approach that combines RL and supervised learning. Furthermore, we investigate permutation invariance and generalization to unseen JSSP instances. Initially, RL policies are trained on Taillard instances for 1800 seconds using Proximal Policy Optimization (PPO). These policies generate data sets of state-action pairs, augmented with varying permutation percentages to transpose job orders. The final step uses the generated data sets f or retraining in a supervised learning setup, focusing on permutation invariance and dropout layers to improve robustness. Our approach (1) improves robustness regarding unseen instances by reducing the mean makespan and standard deviation after outlier removal by -0.43% and -15.31%, respectively, and (2) demonstrates the effect of job order permutations in supervised learning regarding the mean makespan and standard deviation. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.116.20.108

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Schmidl, C.; Simão, T. and Jansen, N. (2024). A Supervised Learning Approach to Robust Reinforcement Learning for Job Shop Scheduling. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4; ISSN 2184-433X, SciTePress, pages 1324-1335. DOI: 10.5220/0012473600003636

@conference{icaart24,
author={Christoph Schmidl. and Thiago Simão. and Nils Jansen.},
title={A Supervised Learning Approach to Robust Reinforcement Learning for Job Shop Scheduling},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={1324-1335},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012473600003636},
isbn={978-989-758-680-4},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - A Supervised Learning Approach to Robust Reinforcement Learning for Job Shop Scheduling
SN - 978-989-758-680-4
IS - 2184-433X
AU - Schmidl, C.
AU - Simão, T.
AU - Jansen, N.
PY - 2024
SP - 1324
EP - 1335
DO - 10.5220/0012473600003636
PB - SciTePress