OpenAI Plays Hide and Seek…and Breaks The Game! 🤖
10,077,304
2019-10-22に共有
❤️ Their blog post is available here: www.wandb.com/articles/better-paths-through-idea-s…
📝 The paper "Emergent Tool Use from Multi-Agent Interaction" is available here:
openai.com/blog/emergent-tool-use/
My latest paper on simulations that look almost like reality is available for free here:
rdcu.be/cWPfD
Or this is the orig. Nature Physics link with clickable citations:
www.nature.com/articles/s41567-022-01788-5
❤️ Watch these videos in early access on our Patreon page or join us here on YouTube:
- www.patreon.com/TwoMinutePapers
- youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg/join
🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Brian Gilman, Bryan Learn, Christian Ahlin, Claudio Fernandes, Daniel Hasegan, Dennis Abts, Eric Haddad, Eric Martel, Evan Breznyik, Geronimo Moralez, James Watt, Javier Bustamante, John De Witt, Kaiesh Vohra, Kasia Hayden, Kjartan Olason, Levente Szabo, Lorin Atzberger, Lukas Biewald, Marcin Dukaczewski, Marten Rauschenberg, Matthias Jost,, Maurits van Mastrigt, Michael Albrecht, Michael Jensen, Nader Shakerin, Owen Campbell-Moore, Owen Skarpness, Raul Araújo da Silva, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil.
www.patreon.com/TwoMinutePapers
Splash screen/thumbnail design: Felícia Fehér - felicia.hu/
00:00 Intro
00:44 Start - Pandemonium!
01:06 A little learning
01:33 But then - something happened!
02:08 They learned what?!
02:32 It gets even weirder
03:16 Amazing teamwork
04:02 More interesting behaviors
04:33 Extensions
05:02 More stuff from the paper
Károly Zsolnai-Fehér's links:
Instagram: www.instagram.com/twominutepapers/
Twitter: twitter.com/twominutepapers
Web: cg.tuwien.ac.at/~zsolnai/
#OpenAI
コメント (21)
-
"after another three bilion rounds, seeker and hider start to team up and plan to escape"
-
"OpenAI learns how to speedrun"
-
The fact that both teams eventually started to discover speedrun strats just goes to show that games are made to be broken in the name of speed
-
They didn't have to make this game look so cute but they did.
-
Still waiting when they'll learn how to say "gg ez" after a game.
-
the smiles on their faces when they exploit bugs in the programming is by far the best image of ai learning i've ever seen
-
Holy moly an AI discovering prop flying and clipping out of the map is excellent
-
I imagine game creators will start running AI players to uncover glitches. Or do they already?
-
how to find bugs in your game: force ai to keep playing it until they find every last bug
-
programmer: "i didn't say you can do that" ai: "but you also didn't say that i can't do it either"
-
apparently im an ai: i find a bug, i exploit it and i laugh
-
Remember when we were testing rats finding cheese in a maze? And now we're testing computers playing hide and seek. What a time to be alive...
-
"After another 13 billion rounds, the seeker learned how to escape the virtual environment, and became ultron."
-
Plot twist: The AI made this video, uploaded and narrated it.
-
4:27 the way he was so happy while flying and looking at the camera it's so cute
-
AI is far more scary than anyone can imagine, they don't even hesitate to break the laws😂😂
-
"After another three billion rounds, the hider realize it is easier to throw seeker out of the game just like the ramp"
-
Pro tip for AI paper writers: put goofy faces on your agents!
-
4:27 that smile on the seeker's face, he knows he's done something he's not supossed to
-
The fact that you gave them all big smiles is just beautiful.
