Twitter | Pretraživanje | |
OpenAI
We're releasing "Dota 2 with Large Scale Deep Reinforcement Learning", a scientific paper analyzing our findings from our 3-year Dota project: One highlight — we trained a new agent, Rerun, which has a 98% win rate vs the version that beat .
Reply Retweet Označi sa "sviđa mi se" More
OG 13. pro
Odgovor korisniku/ci @OpenAI
Wow! The paper looks insanely good! Also nice try calling the new agent Rerun but we can't guarantee you the Bo3 would end the same way in case of a rematch 😏
Reply Retweet Označi sa "sviđa mi se"
Murat Karademir 13. pro
Odgovor korisniku/ci @OGesports @OpenAI @karoly_zsolnai
Wow, OG team endorses OpenAI paper on twitter. What a time to be alive
Reply Retweet Označi sa "sviđa mi se"
Yaroslav Kuznetsov 13. pro
Odgovor korisniku/ci @OpenAI @OGesports
I thought you stopped working on bots for DotA
Reply Retweet Označi sa "sviđa mi se"
l̴o̴o̴p̴u̴l̴e̴a̴s̴a̴ 15. pro
Odgovor korisniku/ci @just_NS @OpenAI @OGesports
I'm happy they didn't
Reply Retweet Označi sa "sviđa mi se"
Alexandre J. Tourville 13. pro
Odgovor korisniku/ci @OpenAI @OGesports
Will we get to see Rerun compete versus human pro teams?
Reply Retweet Označi sa "sviđa mi se"
Roman Lepokhin 13. pro
Odgovor korisniku/ci @OpenAI @OGesports
You dropped dota bots. Didn't you?
Reply Retweet Označi sa "sviđa mi se"
G C 13. pro
Odgovor korisniku/ci @OpenAI @Martian_Will
You might find this 👆🏼 interesting.
Reply Retweet Označi sa "sviđa mi se"
Will.Fs 13. pro
Odgovor korisniku/ci @SmileSimplify @OpenAI
Cool! Thanks!
Reply Retweet Označi sa "sviđa mi se"
Mister Smith 13. pro
Odgovor korisniku/ci @OpenAI @OGesports
Reply Retweet Označi sa "sviđa mi se"