I want reinforcement learning in this model to find the optimal schedule.

Question

question

mark zhen asked Sep 30, '22 Jeanette F commented Oct 20, '22

I want reinforcement learning in this model to find the optimal schedule.

As the question says, I now have a very simple production line, and I hope to use machine learning to learn the optimal scheduling sequence to minimize production time.0816____.fsm

Also, I would like to know why there is such a result

In addition, according to my understanding of the case model, I understand that it is to learn how to generate a good production schedule by random pulling of the machine. In the model I provided, what I want to accomplish is almost the same. I only have five machines now. I wonder if the overall processing can be regarded as a complete event, then how should I set it in reinforcement learning?

Software Version:

FlexSim 22.0.0

reinforcement learning machine learning

1664535803057.png (276.4 KiB)

0816.fsm (310.9 KiB)

· 1

5 |100000

Attachments: Up to 12 attachments (including images) can be used with a maximum of 23.8 MiB each and 47.7 MiB total.

Jeanette F ♦♦ commented · Oct 20, 2022 at 07:50 PM

Hi @mark zhen , was Jeanette 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.

0 ·

Answer 1 · 2022-10-03T16:37:09Z

Jeanette F answered Oct 3, '22 mark zhen commented Oct 18, '22

Hello @mark zhen,

You only set up the Reinforcement Learning for the first processor. That why you are only seeing it act for the first one. Also you are using an express version of FlexSim because there are no random streams. You cannot use Reinforcement Learning when there is no statistical variation.

Please contact your local distributor for assistance with a FlexSim License.

· 7

5 |100000

Attachments: Up to 12 attachments (including images) can be used with a maximum of 23.8 MiB each and 47.7 MiB total.

mark zhen commented · Oct 03, 2022 at 05:11 PM

So does each machine have the same reinforcement learning settings? Could you please teach it?

0 ·

Jeanette F ♦♦ mark zhen commented · Oct 03, 2022 at 05:17 PM

In the Reinforcement Learning GUI you will set up the same things for each processor. For instance when you look at your event trigger and your observations. They are only for you Processor 1. Add the other processors.

You still will not be able to get any results or learning without a FlexSim License. Please contact SimWeb. @Steven Chen

0 ·

mark zhen Jeanette F ♦♦ commented · Oct 05, 2022 at 05:09 PM

0816排程模擬.fsm

I want to know if it's okay for me to set up like this?

0 ·

0816排程模擬.fsm (310.4 KiB)

Show more comments

question