TY - GEN
T1 - A Deep Reinforcement Learning Framework for Capacitated Facility Location Problems with Discrete Expansion Sizes
AU - Zhao, Zhonghao
AU - Lee, Carman K.M.
AU - Yan, Xiaoyuan
AU - Wang, Haonan
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023/12
Y1 - 2023/12
N2 - Capacitated facility location problem (CFLP) is a classical combinatorial optimization problem widely applied in the domains of distribution, transportation planning, and telecommunication. As a typical NP-hard optimization problem, CFLPs featured by combinatorially high-dimensional decision spaces are not easily solved by most conventional methods. To appropriately handle the hard nature of CFLPs, we propose a deep reinforcement learning (DRL)-based framework to address CFLPs with discrete expansion sizes. Since a solution to the investigated CFLP can be sequentially constructed by partial solutions, we reformulated the CFLP as a Markov decision process with an unfixed and discrete time horizon. A deep Q-network (DQN)-based framework is adopted to learn the policy parameters and location solution. We experimentally demonstrate that our proposed approach can effectively find near-optimal solutions for CFLPs.
AB - Capacitated facility location problem (CFLP) is a classical combinatorial optimization problem widely applied in the domains of distribution, transportation planning, and telecommunication. As a typical NP-hard optimization problem, CFLPs featured by combinatorially high-dimensional decision spaces are not easily solved by most conventional methods. To appropriately handle the hard nature of CFLPs, we propose a deep reinforcement learning (DRL)-based framework to address CFLPs with discrete expansion sizes. Since a solution to the investigated CFLP can be sequentially constructed by partial solutions, we reformulated the CFLP as a Markov decision process with an unfixed and discrete time horizon. A deep Q-network (DQN)-based framework is adopted to learn the policy parameters and location solution. We experimentally demonstrate that our proposed approach can effectively find near-optimal solutions for CFLPs.
KW - Capacitated facility location problem
KW - deep Q-network
KW - reinforcement learning
UR - http://www.scopus.com/inward/record.url?scp=85186083757&partnerID=8YFLogxK
U2 - 10.1109/IEEM58616.2023.10406899
DO - 10.1109/IEEM58616.2023.10406899
M3 - Conference article published in proceeding or book
AN - SCOPUS:85186083757
T3 - 2023 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2023
SP - 640
EP - 644
BT - 2023 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2023
Y2 - 18 December 2023 through 21 December 2023
ER -