CS_ALearn/deep-rl-class
1
0
Fork 0
mirror of https://github.com/huggingface/deep-rl-class.git synced 2026-04-26 11:51:19 +08:00
Code Issues Projects Releases Wiki Activity

Merge pull request #575 from carschandler/patch-1

Browse Source 
Confusing wording in self-play.mdx
This commit is contained in:
Thomas Simonini
2024-12-20 11:54:32 +01:00
committed by GitHub
parent d411ceaf93 1c1cf48d3c
commit dba30ddd69
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
units/en/unit7/self-play.mdx
View File

@@ -37,7 +37,7 @@ The theory behind self-play is not something new. It was already used by Arthur
Self-Play is integrated into the MLAgents library and is managed by multiple hyperparameters that we’re going to study. But the main focus, as explained in the documentation, is the **tradeoff between the skill level and generality of the final policy and the stability of learning**.
Training against a set of slowly changing or unchanging adversaries with low diversity **results in more stable training. But a risk to overfit if the change is too slow.**
Training against a set of slowly changing or unchanging adversaries with low diversity **results in more stable training. But there is a risk of overfitting if the change is too slow.**
So we need to control: