Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
karmapolice
on June 1, 2016
|
parent
|
context
|
favorite
| on:
Deep Reinforcement Learning: Pong from Pixels
With further training I don't think it's possible: since those movements are not useful nor harmful, they will appear in winning and losing matches. A possible solution might be including some distance traveled metric in the reward function...
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: