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
We're releasing "Dota 2 with Large Scale Deep Reinforcement Learning", a scientific paper analyzing our findings from our 3-year Dota project: https://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
-
-
-
Wow, OG team endorses OpenAI paper on twitter. What a time to be alive
@karoly_zsolnai - Još 1 odgovor
Novi razgovor -
-
-
I thought you stopped working on bots for DotA
-
I'm happy they didn't
Kraj razgovora
Novi razgovor -
-
-
Will we get to see Rerun compete versus human pro teams?
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
You dropped dota bots. Didn't you?
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
@Martian_Will You might find this
interesting. -
Cool! Thanks!
Kraj razgovora
Novi razgovor -
-
-
Tweet je nedostupan.
Novi razgovor
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.