Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
allenz
on Dec 6, 2017
|
parent
|
context
|
favorite
| on:
Mastering Chess and Shogi by Self-Play with Genera...
It's unclear how much of the "better representation" was due to better algorithm vs. more compute/deeper NN.
joshuamorton
on Dec 7, 2017
[–]
Giraffe was trained until convergence. Maybe if there was more compute power then, a different model would have been used, but that's deep into the world of silly hypotheticals.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
