TY - JOUR
T1 - Scalable decentralised approaches for job shop scheduling
AU - Martinez Jimenez, Yailen
AU - Tony, Wauters
AU - Patrick, De Causmaecker
AU - Verbeeck, Katja
PY - 2010/7
Y1 - 2010/7
N2 - We present two Reinforcement Learning approaches for the Parallel Machines Job Shop Scheduling Problem. The objective used is the minimization of the schedule makespan. We study two approaches, one where resources are modeled as intelligent agents and have to choose what operation to process next, and an other where operations themselves are seen as the agents that have to choose their mutual scheduling order. We use a value iteration method (QLearning) and a policy iteration method (Learning Automata). The results of both approaches improve on recently published results from the literature and we argue that they exhibit better scaling behavior. We validate our approaches by applying them to the flexible job shop scheduling problem where operations can be executed on any of a number of available machines
AB - We present two Reinforcement Learning approaches for the Parallel Machines Job Shop Scheduling Problem. The objective used is the minimization of the schedule makespan. We study two approaches, one where resources are modeled as intelligent agents and have to choose what operation to process next, and an other where operations themselves are seen as the agents that have to choose their mutual scheduling order. We use a value iteration method (QLearning) and a policy iteration method (Learning Automata). The results of both approaches improve on recently published results from the literature and we argue that they exhibit better scaling behavior. We validate our approaches by applying them to the flexible job shop scheduling problem where operations can be executed on any of a number of available machines
KW - Reinforcement Learning
KW - Scheduling Problems
M3 - Editorial
JO - Proceedings of the 24th European Conference on Operational Research EURO XXIV
JF - Proceedings of the 24th European Conference on Operational Research EURO XXIV
ER -