-
-
Notifications
You must be signed in to change notification settings - Fork 111
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
Implementation of NFSP and NFSP_KuhnPoker experiment #402
Implementation of NFSP and NFSP_KuhnPoker experiment #402
Conversation
Please remember to fix the failed CI first. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks much better. Well done! I'll verify the implementation on some other games tomorrow.
src/ReinforcementLearningZoo/src/algorithms/nfsp/nfsp_example.jl
Outdated
Show resolved
Hide resolved
src/ReinforcementLearningZoo/src/algorithms/nfsp/nfsp_example.jl
Outdated
Show resolved
Hide resolved
src/ReinforcementLearningZoo/src/algorithms/nfsp/nfsp_extensions.jl
Outdated
Show resolved
Hide resolved
@@ -0,0 +1,140 @@ | |||
export NFSPAgent |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Just name this file as nfsp.jl
?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for your kind suggestions!
I'll merge nfsp_example.jl
and nfsp_extensions.jl
to nfsp.jl
, and move NFSPAgent setting details to the experiment file later.
Please remember to fix the failed CI first.
I'll fix the spellcheck later. And I don't know how to fix the Documentation error. 😞
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Use ##
in the comments of JuliaRL_NFSP_KuhnPoker.md
file instead of #
.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks! I'll update the file soon.
This PR is for recording my implementation of Neural Fictitious Self-play(NFSP) algorithm and its relative experiments. Former discussions are in #375 #386.