Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Anderkent
on July 19, 2018
|
parent
|
context
|
favorite
| on:
OpenAI Five Benchmark
Same argument applies to pushing and defending towers, getting rax etc. Assuming that the devs did not hardcode rewards for those objectives, then the AI surely already has to 'understand' events that impact the game in long term.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: