Replies: 1 comment
-
Actually, I'm thinking now that the randomization of # tasks, which subset and ordering of the training tasks would be enough to help avoid local optima, which I think is the main advantage of POET |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I watched this lecture yesterday and thought it would be interesting to include it: https://youtu.be/5jL5wRGrCvk
Here are the papers (didn't read them yet):
Would the skill tree just be a default curriculum and then revert to POET or Enhanced POET?
Beta Was this translation helpful? Give feedback.
All reactions