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
Will we get to see Rerun compete versus human pro teams?
09:36 - 13. pro 2019.
0 replies
0 proslijeđenih tweetova
9 korisnika označava 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.