Multi-Agent Hide and Seek

Переглядів 1 355 164
99% 74 320 563

We’ve observed agents discovering progressively more complex tool use while playing a simple game of hide-and-seek. Through training in our new simulated hide-and-seek environment, agents build a series of six distinct strategies and counterstrategies, some of which we did not know our environment supported. The self-supervised emergent complexity in this simple environment further suggests that multi-agent co-adaptation may one day produce extremely complex and intelligent behavior.
Learn more: openai.com/blog/emergent-tool-use/

Наука та технологія



17 вер 2019





Додати в:

Мій плейлист
Переглянути пізніше
mohammed bilal kolkar
mohammed bilal kolkar 9 годин тому
Hiders can box the seekers ,problem solved for seekers that use other object to jump over and totally in lockdown
Ee Cheng LEE
Ee Cheng LEE 16 годин тому
didn't expect people to be meme-ing down here not complaining tho •ᴗ•
Loop День тому
now, this is a open world game i would like to play
Loop 10 годин тому
@John DC ofc they can, whole AI system is actually based on reward and penalty system
John DC
John DC 10 годин тому
@Loop even better if the NPCs can somehow learn to give players apporopriate quests and rewards based on what they want. Everything would basically be procedural and you would actually be shaping your own world alongside the NPCs.
Loop 10 годин тому
​ John DC Exactly, and as a developer, instead of building boring and liner quests, you would only implement game dynamics and let NPC's decide for them selves what they want to do.
John DC
John DC 11 годин тому
Dude imagine if you just had an open world game that also included learning NPCs that have neural nets. You'd have a whole world that changes artificially from the players and naturally from other AIs. Probably gonna be a PC killer though lol
Igor Gabrielan
Igor Gabrielan 2 дні тому
Harry 2 дні тому
And this my gamers is the *recommended page*
Late night talk show with the Bronson
mr. grootex
mr. grootex 2 дні тому
Is that a game!?!?!?!?!
João Ramon Gomes Da Silva
João Ramon Gomes Da Silva 3 дні тому
Very nice, i wold like to see more strategy games...
4ammofo 3 дні тому
competition? it was cooperation to survive that led us to where we are u dingus.
Bratteries and Snignals
Bratteries and Snignals 3 дні тому
That's intelligent, yet scary. applying such algorithms on machines. you know the rest.
ChuckNorris100000 4 дні тому
Elon’s brain nightmares are coming back to haunt him.
kiko synth
kiko synth 4 дні тому
Next Gen Games
Next Gen Games 4 дні тому
That's insane...u can drop this last AI generation in Mars & let them build simple buildings & wiring throw the walls...insane
Ganymede, Jupiter III
Ganymede, Jupiter III 5 днів тому
SkyNet liked this video
Kick Lee
Kick Lee 6 днів тому
Instead of hiding from the red ones they should locked the red ones by the blocks .
Xuezhou Zhang
Xuezhou Zhang 6 днів тому
If you know the rule of the game, it's not hard to figure out the hiders ultimate strategy: lock all blocks and wall themselves. On the contrary, these RL agents learn these simple strategies by playing millions or perhaps billions of games. This is NOT how humans or other animals perform problem-solving. We do not solve puzzles by attempting them several million times. We simply cannot afford to do so. Instead, we solve problems by abstracting them and reason about them. That is called intelligence. RL is NOT the golden path to intelligence, it is a path to problem-solving with NO intelligence, contrary of what the vision of general artificial intelligence is aiming for.
Jay Sukumalchan
Jay Sukumalchan 7 днів тому
Imagine someday OpenAI will work with Boston to make Sky net.
Azeri Lyrics
Azeri Lyrics 7 днів тому
bomba kimi
YoseiHito 7 днів тому
The fact that it learned all of that by itself is insane and a huge step towards self aware ai.
Gustav Isak Abrahamsson
Gustav Isak Abrahamsson 7 днів тому
alternate title: making AI use Half-Life 2 speedrun strategies
WulfCry 8 днів тому
Expecting spontaneous combustion with the agents as saying auto-intelligence will emerge with more simulation. The maximum of what they can is bound by the physic rules of the environment perceived by these agents. Their call is confined to one layer of the environment that makes them interact the way they do.
Jack Napier
Jack Napier 8 днів тому
This is witchcraft! WOW!
Football addicts
Football addicts 8 днів тому
Idk how this cane up on recommended but it's actually pretty cool
Bhuvanesh s.k
Bhuvanesh s.k 8 днів тому
Hiders atlast ran out of tht stage....?? Is tht so
Bhuvanesh s.k
Bhuvanesh s.k 8 днів тому
PPL 50 years ago:- science can never explain feelings and thoughts like love, logic etc etc.... Currently... Reinforcement Learning an mathematical model...!!! Can mimic tht process imagine the power we are literally speeding up the evolution of millions of years to few weeks with these simulators and fast TPUs or GPUs... This is crazyyy
Abe Alexander
Abe Alexander 8 днів тому
Welcome to the Aperture Science computer-aided enrichment center.
Leeroy Jenkins
Leeroy Jenkins 8 днів тому
Seeing them yoink the ramp from the seekers is so funny for some reason lol
David Baumann
David Baumann 8 днів тому
oh yeah, this is big brain thime
Bloodcrow 100
Bloodcrow 100 8 днів тому
Can someone make this a game
Ocrael 8 днів тому
1:52 They're starting to think like Gurdan Freemon
Ephraim Cullen
Ephraim Cullen 8 днів тому
"One day, truly complex and intelligent agents will emerge." I hope not. Skynet will not be a picnic.
Anson Chan
Anson Chan 9 днів тому
Im surprised they didn't trap them
Jamil Madanat
Jamil Madanat 9 днів тому
I don't think we'll reach 'truly intelligent' .. I can't foresee designing an environment that mimics "real life"
YoseiHito 7 днів тому
@Jamil Madanat I see what you're saying but I've heard many times that the data required for self awareness is achievable, it's just way too much information for today's technology, the ai you see right now is aware of its environments that's why it's capable of reacting to it without programming so at some point in life, it's gonna be capable of comprehending life, I don't think it's impossible.
Jamil Madanat
Jamil Madanat 7 днів тому
@YoseiHito self awarness is precisely what i find impossible to achieve.. We dont understand consciousness nor where it comes from. How can we assume that self-learning will be followed by self-awarness?
YoseiHito 7 днів тому
If the ai "self learn" techniques keep evolving, it can get to the point where they become self aware of themselves, humans, emotions etc and that probably would make them able to mimic humans and other beings.
ZICHEN JIE 9 днів тому
Ultron, come and teach these two little ones how to play hide and seek
McQ 9 днів тому
Nature inspires art. Not the other way around.
Colox 9 днів тому
this video is very cute
JuN Bearded
JuN Bearded 9 днів тому
Open AI + Boston Dynamics = we'll all die soon !
loYol 9 днів тому
They deadass just made hide and seek bots
Weazel 9 днів тому
So tired of machine learning. This is not 'learning'. What you are watching is a computer program that is run so many times that it finally, accidentally, stumbles upon a correction solution, which it isn't even aware that it has stumbled upon. It then takes a human to pick the best outcome, which the program doesn't know was a good outcome, and then help the program cheat the next set of runs it does by telling the program that it should behave more like the way the programmer selected. Again, this is NOT machine learning. So tired of how the media covers this topic and how programmer never correct them. "Note that we did not explicitly incentivize any of these behaviors" Bullshit. Absolute bullshit. When you tell the program which strategy to implement from the previous round, you are explicitly giving the program human input.
hefe batsen
hefe batsen 9 днів тому
2:49 ... and wipe humanity the fuck out.
Grigor Yeghiazaryan
Grigor Yeghiazaryan 9 днів тому
Elon, be careful not to loose them, they can hide from you 😁
FieldSweeper 9 днів тому
see no matter what rules you are given in a game. people will always try to break them hahaha
#theofficial_ kami
#theofficial_ kami 9 днів тому
Yeahhhh We're teaching them to kill us in futute.
USBEN 9 днів тому
Those faces adorable .
a little boy
a little boy 9 днів тому
"This works by algorithms." No way, really? A little more information would be appreciated.
nineof8 9 днів тому
OpenAI is a precursor to the simulation we'll find ourselves in
Yahya Jaber
Yahya Jaber 9 днів тому
wafflepiepancake 9 днів тому
Andrew Yang warned us about this. #YangGang2020
hotkulboi77 9 днів тому
*meanwhile dumb ass muslims want to take this civilization 1000 of years back*
SeungHyun 10 днів тому
Trump: *builds wall* Mexican surfer : "hola amigo"
Keylo moon
Keylo moon 10 днів тому
is this deep learning?
Glamour Window Tinting
Glamour Window Tinting 10 днів тому
good to see they evolved in defense not offense. be worried when they start boxing in the seekers first and free to walk around.
Esdras Cardona
Esdras Cardona 10 днів тому
Daniel 10 днів тому
If this was a game I'd play it.
hi svnz
hi svnz 10 днів тому
can we actually get this as a VIDEO GAME????
Artur Kucina
Artur Kucina 10 днів тому
Why Hiders just don't block Seekers at the beginning?
nigelwestdickens 10 днів тому
The birth of skynet
Real Yukthivadhi
Real Yukthivadhi 10 днів тому
After 20000 years AI will not believe in Humans
Переглядів 1 278 412
Dark Passage | League of Legends
Переглядів 1 021 522
Multi-agent Reinforcement Learning
Переглядів 644
Multi-agent simulation with Python
Переглядів 335
I Tried Escaping A Bounty Hunter
Переглядів 20
Проверка 14 бьюти лайфхаков