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
-
-
Odgovor korisnicima @OpenAI @OGesports
I thought you stopped working on bots for DotA
1 reply 0 proslijeđenih tweetova 14 korisnika označava da im se sviđa
I'm happy they didn't
05:55 - 15. pro 2019.
0 replies
0 proslijeđenih tweetova
3 korisnika označavaju da im se sviđa
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.