We've observed AIs discovering complex tool use while competing in a simple game of hide-and-seek. They develop a series of six distinct strategies and counterstrategies, ultimately using tools in the environment to break our simulated physics:https://openai.com/blog/emergent-tool-use …
-
Prikaži ovu nit
-
Odgovor korisniku/ci @OpenAI
hardmaru je proslijedio/a tweet korisnika/ceOpenAI
Congrats on this very inspiring work! I'd be interested to see this line of work scale up in a way proposed in your previous paper on Neural MMO paper:https://twitter.com/OpenAI/status/1102614211237097472 …
hardmaru je dodan/na,
OpenAIOvjeren akaunt @OpenAIWe’re releasing a Neural MMO — a massively multiagent game environment that supports numerous populations of agents: https://blog.openai.com/neural-mmo/ - Code: https://github.com/openai/neural-mmo … - 3D Client: https://github.com/jsuarez5341/neural-mmo-client … pic.twitter.com/tEVPjxE7yP14 proslijeđenih tweetova 110 korisnika označava da im se sviđa
I desire nothing more than the opportunity to do so. Have been hard at work on Neural MMO since the v1.0 release -- lots of progress since:pic.twitter.com/PXvkEEK2XP
00:15 - 18. ruj 2019.
0 replies
0 proslijeđenih tweetova
14 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.