TY - GEN
T1 - Hierarchical Deep Reinforcement Learning Approach for Multi-Objective Scheduling with Varying Queue Sizes
AU - Birman, Yoni
AU - Ido, Ziv
AU - Katz, Gilad
AU - Shabtai, Asaf
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/9/21
Y1 - 2021/9/21
N2 - Multi-objective task scheduling (MOTS) combines the task of scheduling with the need to optimize multiple-and possibly contradicting-constraints. A challenging extension of this problem occurs when every individual task is a multiobjective optimization problem by itself. While deep reinforcement learning (DRL) has been successfully applied to complex sequential problems, its application to the MOTS domain has been stymied by two challenges. The first challenge is the inability of the DRL algorithm to ensure that every item is processed identically regardless of its position in the queue. The second challenge is the need to manage large queues, which results in large neural architectures and long training times. In this study we present MERLIN, a robust, modular and near-optimal DRL-based approach for multi-objective task scheduling. Our approach addresses both aforementioned challenges while also being more efficient and easier to train. Extensive evaluation on multiple queue sizes show that MERLIN outperforms multiple well-known scheduling algorithms by a large margin (≥ 22%).
AB - Multi-objective task scheduling (MOTS) combines the task of scheduling with the need to optimize multiple-and possibly contradicting-constraints. A challenging extension of this problem occurs when every individual task is a multiobjective optimization problem by itself. While deep reinforcement learning (DRL) has been successfully applied to complex sequential problems, its application to the MOTS domain has been stymied by two challenges. The first challenge is the inability of the DRL algorithm to ensure that every item is processed identically regardless of its position in the queue. The second challenge is the need to manage large queues, which results in large neural architectures and long training times. In this study we present MERLIN, a robust, modular and near-optimal DRL-based approach for multi-objective task scheduling. Our approach addresses both aforementioned challenges while also being more efficient and easier to train. Extensive evaluation on multiple queue sizes show that MERLIN outperforms multiple well-known scheduling algorithms by a large margin (≥ 22%).
KW - Computer Science - Machine Learning
KW - Computer Science - Cryptography and Security
KW - Statistics - Machine Learning
UR - http://www.scopus.com/inward/record.url?scp=85116471487&partnerID=8YFLogxK
U2 - 10.1109/IJCNN52387.2021.9534433
DO - 10.1109/IJCNN52387.2021.9534433
M3 - Conference contribution
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 1
EP - 10
BT - IJCNN 2021 - International Joint Conference on Neural Networks, Proceedings
PB - Institute of Electrical and Electronics Engineers
T2 - 2021 International Joint Conference on Neural Networks, IJCNN 2021
Y2 - 18 July 2021 through 22 July 2021
ER -