Dynamic job-shop scheduling using reinforcement learning agents

Aydın, Mehmet Emin; Öztemel, Ercan

doi:10.1016/s0921-8890(00)00087-7

Cited by 208 publications

(96 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They receive messages from the environment using the perception mechanism, evaluate the messages using the cognition module, and produce actions by the action module [5,51,52]. Learning and evolving are key mechanisms in intelligent agents.…”

Section: Reinforcement Learningmentioning

confidence: 99%

“…RL has been applied to manufacturing scheduling [51,[53][54][55][56][57][58][59]. A single machine agent used Q-learning to determine if it could learn commonly accepted dispatching rules for three example cases in which the best dispatching rules had been previously defined in Wang and Usher [53].…”

Section: Reinforcement Learningmentioning

confidence: 99%

“…A single machine agent used Q-learning to determine if it could learn commonly accepted dispatching rules for three example cases in which the best dispatching rules had been previously defined in Wang and Usher [53]. Agents were trained to an RL algorithm, called Q-III, used for dynamic job shop scheduling to select the most appropriate priority rule according to the shop conditions in real time in Aydin and Oztemel [51]. The temporal difference algorithm TD(λ), an RL algorithm, has been applied to job shop scheduling involving the scheduling of the various tasks that had to be performed to install and test the payloads placed in the cargo bay of the NASA space shuttle for each mission [54].…”

Section: Reinforcement Learningmentioning

confidence: 99%

See 2 more Smart Citations

Manufacturing Scheduling Using Colored Petri Nets and Reinforcement Learning

Drakaki

Tzionas

2017

Applied Sciences

View full text Add to dashboard Cite

Agent-based intelligent manufacturing control systems are capable to efficiently respond and adapt to environmental changes. Manufacturing system adaptation and evolution can be addressed with learning mechanisms that increase the intelligence of agents. In this paper a manufacturing scheduling method is presented based on Timed Colored Petri Nets (CTPNs) and reinforcement learning (RL). CTPNs model the manufacturing system and implement the scheduling. In the search for an optimal solution a scheduling agent uses RL and in particular the Q-learning algorithm. A warehouse order-picking scheduling is presented as a case study to illustrate the method. The proposed scheduling method is compared to existing methods. Simulation and state space results are used to evaluate performance and identify system properties.

show abstract

Section: Reinforcement Learningmentioning

confidence: 99%

Section: Reinforcement Learningmentioning

confidence: 99%

Section: Reinforcement Learningmentioning

confidence: 99%

See 1 more Smart Citation

Manufacturing Scheduling Using Colored Petri Nets and Reinforcement Learning

Drakaki

Tzionas

2017

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The dynamic JSSP incorporates uncertainty with respect to the number of jobs and the release dates associated with the jobs which are to be scheduled (Aydin andOztemel 2000 andQi et al 2000), while the stochastic JSSP focuses on incorporating uncertainty into the process time estimates (Lei and Xiong 2007;Singer 2000;and Yoshitomi and Yamaguchi 2003).…”

Section: The Problem Contextmentioning

confidence: 99%

Metaheuristics for the multi-objective FJSP with sequence-dependent set-up times, auxiliary resources and machine down time

Grobler

Engelbrecht²,

Kok³

et al. 2009

Ann Oper Res

View full text Add to dashboard Cite

This paper investigates the application of particle swarm optimization (PSO) to the multi-objective flexible job shop scheduling problem with sequence-dependent set-up times, auxiliary resources and machine down time. To achieve this goal, alternative particle representations and problem mapping mechanisms were implemented within the PSO paradigm. This resulted in the development of four PSO-based heuristics. Benchmarking on real customer data indicated that using the priority-based representation resulted in a significant performance improvement over the existing rule-based algorithms commonly used to solve this problem. Additional investigation into algorithm scalability led to the development of a priority-based differential evolution algorithm. Apart from the academic significance of the paper, the benefit of an improved production schedule can be generalized to include cost reduction, customer satisfaction, improved profitability, and overall competitive advantage.

show abstract

“…Aydin andÖztemel [2] describe a system for solving dynamic job shop sequencing problems using intelligent agents. In this paper, an agent does not solve a complete problem, but simply reacts to the requests from a simulated environment and develops an appropriate job priority list.…”

Section: Industrial Manufacturingmentioning

confidence: 99%

Dynamic Problems and Nature Inspired Meta-Heuristics

Hendtlass¹,

Moser²,

Randall³

2006

2006 Second IEEE International Conference on E-Science and Grid Computing (E-Science'06)

View full text Add to dashboard Cite

Biological systems are, by their very nature, adaptive. However, the meta-heuristic search algorithms inspired by them have mainly been applied to static problems (i.e., problems that do not change while they are being solved). Recently, a greater body of work has been completed on the newer meta-heuristics, particularly ant colony optimisation, particle swarm optimisation and extremal optimisation. This survey paper examines representative works and methodologies of these techniques on this class of problems. Beyond this we outline the limitations of these methods.

show abstract

Dynamic job-shop scheduling using reinforcement learning agents

Cited by 208 publications

References 27 publications

Manufacturing Scheduling Using Colored Petri Nets and Reinforcement Learning

Manufacturing Scheduling Using Colored Petri Nets and Reinforcement Learning

Metaheuristics for the multi-objective FJSP with sequence-dependent set-up times, auxiliary resources and machine down time

Dynamic Problems and Nature Inspired Meta-Heuristics

Contact Info

Product

Resources

About