Skip to content

Conversation

peterchen96
Copy link
Member

This PR is for recording my implementation of Neural Fictitious Self-play(NFSP) algorithm and its relative experiments. Former discussions are in #375 #386.

@findmyway
Copy link
Member

Please remember to fix the failed CI first.

Copy link
Member

@findmyway findmyway left a 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.

@@ -0,0 +1,140 @@
export NFSPAgent
Copy link
Member

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 ?

Copy link
Member Author

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. 😞

Copy link
Member

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 #.

Copy link
Member Author

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.

@findmyway findmyway merged commit 0a8b796 into JuliaReinforcementLearning:master Jul 31, 2021
@peterchen96 peterchen96 deleted the peter/NFSP branch August 8, 2021 18:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants