Rewriting the Reward Function

@Kavika F @Jason Lightfoot @Felix Möhlmann

I have now split my reward function into three

But I think it should be similar to the example reward function but I don't know how to rewrite it.rltest-2 (1).fsm

Also, I'm stuck in training now, and I want to ask how to solve it

I think my reward function should be a reward function in the form of a matrix so how do I rewrite

I am currently writing like this but there are still many problems and I can't find any solution

I have no way to execute smoothly in training.py.

Software Version:

FlexSim 22.0.0

· 3

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 · Dec 06, 2022 at 07:48 AM

@Kavika F

I want to discuss the matter of maximizing throughput. My reward function has been rewritten. I also want to ask why my model is connected to the agent to solve the connection model. Something that I can't understand.123.fsm

0 ·

123.fsm (289.3 KiB)

mark zhen mark zhen commented · Dec 06, 2022 at 07:50 AM

This is what my connection proxy looks like.

but when i disconnect the proxy my model becomes like this

0 ·

1670312937670.png (288.0 KiB)

1670313012422.png (263.5 KiB)

Kavika F ♦ commented · Jan 04, 2023 at 06:05 PM

Hi @mark zhen ,

Were you able to solve your problem? If so, please add and accept an answer to let others know the solution.

If we don't hear back in the next 3 business days, we'll assume you were able to solve your problem and we'll close this case in our tracker. You can always comment back at any time to reopen your question, or you can contact your local FlexSim distributor for phone or email help.

0 ·

question