Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
phreeza
on June 1, 2016
|
parent
|
context
|
favorite
| on:
Deep Reinforcement Learning: Pong from Pixels
You could probably do that by introducing a regularization term on the activity. Possibly L1 because that will tend toward sparse outputs.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
