|
@OpenAI | |||||
|
We're releasing "Dota 2 with Large Scale Deep Reinforcement Learning", a scientific paper analyzing our findings from our 3-year Dota project: openai.com/projects/five/
One highlight — we trained a new agent, Rerun, which has a 98% win rate vs the version that beat @OGEsports. pic.twitter.com/1kWvXwBHHp
|
||||||
|
||||||
|
OG
@OGesports
|
13. pro |
|
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 😏
#DreamOG
|
||
|
|
||
|
Murat Karademir
@MuratKun
|
13. pro |
|
Wow, OG team endorses OpenAI paper on twitter. What a time to be alive @karoly_zsolnai
|
||
|
|
||
|
Yaroslav Kuznetsov
@just_NS
|
13. pro |
|
I thought you stopped working on bots for DotA
|
||
|
|
||
|
l̴o̴o̴p̴u̴l̴e̴a̴s̴a̴
@loopuleasa
|
15. pro |
|
I'm happy they didn't
|
||
|
|
||
|
Alexandre J. Tourville
@ajtourville
|
13. pro |
|
Will we get to see Rerun compete versus human pro teams?
|
||
|
|
||
|
Roman Lepokhin
@Casperenush
|
13. pro |
|
You dropped dota bots. Didn't you?
|
||
|
|
||
|
G C
@SmileSimplify
|
13. pro |
|
@Martian_Will You might find this 👆🏼 interesting.
|
||
|
|
||
|
Will.Fs
@Martian_Will
|
13. pro |
|
Cool! Thanks!
|
||
|
|
||
|
Mister Smith
@Jermain84987700
|
13. pro |
|
|
||