I would like to know, machine learning about optimization,
Is there any information on how I can improve the model made by the teaching guide?
(The way I want it to work is as follows, I have 5 products today with a random parameter, and I want to use reinforcement learning to train an optimized production schedule.)
Hi @mark zhen , was Kavika F's answer helpful? If so, please click the "Accept" button at the bottom of their answer. Or if you still have questions, add a comment and we'll continue the conversation.
If we haven't heard back from you within 3 business days we'll auto-accept an answer, but you can always unaccept and comment back to reopen your question.
Here are the docs on Reinforcement Learning Training, Concepts of Reinforcement Learning, and How to Use a Trained Model. This will point you in the right direction and hopefully provide enough detail you're looking for.
I have already practiced the above content, but there is still a gap between what I expected. What I need is something that can be collected into a table. Let me know the order of production scheduling.
Once you have trained the algorithm you can run the model while the algorithm is making decision during the run.
You could then record those decisions or their effect on the model by listening to various events and writing data to a global table.
For example to record the actions the algorithm is taking, you can listen to the RL-event "OnRequestAction" in an event-triggered source (use the sampling tool on the RL entry in the toolbox to select the event). Then have the token wait in a Delay activity for a tiny amount of time (so the request is processed first) and then log the value of the action parameters in a global table.
Similarly, you could log the item types that are processed by listening to some trigger of the processor (OnEntry, OnProcessFinish, ...).
What data you should collect depends on what exactly your desired output is.
但我想要做的事情是類似最佳化生產排程的計算，我該如何利用強化學習來達成這件事。
But what I want to do is something like optimizing production scheduling, and how can I use reinforcement learning to do that?
16 People are following this question.
FlexSim can help you understand and improve any system or process. Transform your existing data into accurate predictions.
FlexSim is a fully 3D simulation software environment. FlexSim can be used to simulate any process in any industry.
FlexSim®, FlexSim Healthcare™, Problem Solved.®, the FlexSim logo, the FlexSim X-mark, and the FlexSim Healthcare logo with stylized Caduceus mark are trademarks of FlexSim Software Products, Inc. All rights reserved.
