-
Notifications
You must be signed in to change notification settings - Fork 1
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
What is Best_Method.p? #1
Comments
It’s a pretrained model that I made by running the program for a long time.
If you replace the q_table with that it will solve the problem in a close
to optimal way.
Uncomment the pickle.load instead of method.train() to load it in.
…On Tue, Sep 22, 2020 at 9:06 PM mmont ***@***.***> wrote:
See title text.
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#1>, or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ACFAJ7AJJR42AAJJMVFJQ3LSHFJ3JANCNFSM4RWOT6JA>
.
|
To be more specific it's a pickle file which is a way to save out and load in python data structures. In general its a easy way to save python data, but you shouldn't run pickles from code you don't trust as they could contain anything. If this was production code you would want to write code to serialize the data in a more safe way. |
Ha... That's interesting. So it contains what? The "optimal" parameters for solving the problem? This is my first time seeing it, entirely unfamiliar with it. |
Its just the values in the q_table after I trained it for an hour or so. Looking at it i don't think it's possible to solve the problem significantly faster, but they're not optimal per se. the output of training a Q Learning method would be the q table which is a model of what actions should be taken at various states. |
See title text.
The text was updated successfully, but these errors were encountered: