Multi-Agent Hide and Seek

  • Am Vor 29 Tage

    OpenAIOpenAI

    Dauer: 2:58

    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/

Jordan Bigby
Jordan Bigby

I’m very disappointed too say I’m here from TikTok 😔

Vor Stunde
zbobz12
zbobz12

That's freaking cool

Vor Stunde
dxxPacmanxxb
dxxPacmanxxb

This is not in-depth enouuugh

Vor 2 Stunden
xX_Kjcomputer_Xx
xX_Kjcomputer_Xx

-until the hider are smart enough to lock the seeker inside the cage

Vor 8 Stunden
The Other Side
The Other Side

*This will be implemented in future robots and then they will learn that we are destructive to yourselves. And then decide that they are the ones best suited to protect us from us. And thus we begin our journey into robotic slavery.*

Vor 9 Stunden
Pseudo X
Pseudo X

He attacc He protecc but most importantly He surfs in buccs

Vor 17 Stunden
Lucas R
Lucas R

So basically it’s slavery with extra steps

Vor 17 Stunden
Dolank
Dolank

Okay seriously wtf, all YouTube comments are just quoting the videos now. This is seriously weird.

Vor 20 Stunden
Lucas R
Lucas R

IKR

Vor 17 Stunden
SMART THOUGHTS
SMART THOUGHTS

Better . Far far better

Vor 23 Stunden
i love love song
i love love song

Tech them to speak

Vor 23 Stunden
Shivam Dhoot
Shivam Dhoot

Which 3D simulation program did they use? Pretty cool stuff though!

Vor Tag
SpaceDave1337
SpaceDave1337

You should make this a Videogame somehow

Vor Tag
Mr. MindReader
Mr. MindReader

Me: Just surround the seekers with walls AI: *Circuits Blown*

Vor Tag
gangster gandalf
gangster gandalf

Im surprised they didnt lock in the seekers

Vor Tag
fl00fydragon
fl00fydragon

Everyone else: AI is learning to hunt us down. Me: AI learned speed run exploits.

Vor Tag
The Potato
The Potato

terminator age is coming. And it's looking so cute.

Vor 2 Tage
HackTor
HackTor

Remember when humans use to play hide and seek?

Vor 2 Tage
Harry
Harry

I wonder if AI will learn how to ABH...

Vor 2 Tage
vijay vittal
vijay vittal

How do I learn to do this?

Vor 2 Tage
DuoBV Channel
DuoBV Channel

these little creatures, reminds me of little big planet Sackboy :,D

Vor 2 Tage
mb k
mb k

Hiders can box the seekers ,problem solved for seekers that use other object to jump over and totally in lockdown

Vor 2 Tage
Ee Cheng LEE
Ee Cheng LEE

didn't expect people to be meme-ing down here not complaining tho •ᴗ•

Vor 3 Tage
Loop
Loop

now, this is a open world game i would like to play

Vor 3 Tage
Loop
Loop

@John DC ofc they can, whole AI system is actually based on reward and penalty system

Vor 3 Tage
John DC
John DC

@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.

Vor 3 Tage
Loop
Loop

​ 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.

Vor 3 Tage
John DC
John DC

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

Vor 3 Tage
Igor Gabrielan
Igor Gabrielan

multi.ai

Vor 4 Tage
Harry
Harry

And this my gamers is the *recommended page*

Vor 4 Tage
Late night talk show with the Bronson
Late night talk show with the Bronson

Uncomfortable

Vor 5 Tage
mr. grootex
mr. grootex

Is that a game!?!?!?!?!

Vor 5 Tage
João Ramon Gomes Da Silva
João Ramon Gomes Da Silva

Very nice, i wold like to see more strategy games...

Vor 5 Tage
4ammofo
4ammofo

competition? it was cooperation to survive that led us to where we are u dingus.

Vor 6 Tage
Bratteries and Snignals
Bratteries and Snignals

That's intelligent, yet scary. applying such algorithms on machines. you know the rest.

Vor 6 Tage
ChuckNorris100000
ChuckNorris100000

Elon’s brain nightmares are coming back to haunt him.

Vor 6 Tage
kiko synth
kiko synth

スゲェ…

Vor 7 Tage
Next Gen Games
Next Gen Games

That's insane...u can drop this last AI generation in Mars & let them build simple buildings & wiring throw the walls...insane

Vor 7 Tage
Ganymede, Jupiter III
Ganymede, Jupiter III

SkyNet liked this video

Vor 8 Tage
Kick Lee
Kick Lee

beautiful

Vor 8 Tage
PARALLEL UNIVERSE
PARALLEL UNIVERSE

Instead of hiding from the red ones they should locked the red ones by the blocks .

Vor 9 Tage
Xuezhou Zhang
Xuezhou Zhang

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.

Vor 9 Tage
Jay Sukumalchan
Jay Sukumalchan

Imagine someday OpenAI will work with Boston to make Sky net.

Vor 10 Tage
Azeri Lyrics
Azeri Lyrics

bomba kimi

Vor 10 Tage
YoseiHito
YoseiHito

The fact that it learned all of that by itself is insane and a huge step towards self aware ai.

Vor 10 Tage
Gustav Isak Abrahamsson
Gustav Isak Abrahamsson

alternate title: making AI use Half-Life 2 speedrun strategies

Vor 10 Tage
EL EXTERMINADOR
EL EXTERMINADOR

AQUI É BR VAI BRASIL TEMOS A AMAZÔNIA

Vor 10 Tage
WulfCry
WulfCry

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.

Vor 10 Tage
Jack Napier
Jack Napier

This is witchcraft! WOW!

Vor 10 Tage
Football addicts
Football addicts

Idk how this cane up on recommended but it's actually pretty cool

Vor 11 Tage
Bhuvanesh s.k
Bhuvanesh s.k

Hiders atlast ran out of tht stage....?? Is tht so

Vor 11 Tage
Bhuvanesh s.k
Bhuvanesh s.k

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

Vor 11 Tage
Abe Alexander
Abe Alexander

Welcome to the Aperture Science computer-aided enrichment center.

Vor 11 Tage
Leeroy Jenkins
Leeroy Jenkins

Seeing them yoink the ramp from the seekers is so funny for some reason lol

Vor 11 Tage
David Baumann
David Baumann

oh yeah, this is big brain thime

Vor 11 Tage
Bloodcrow 100
Bloodcrow 100

Can someone make this a game

Vor 11 Tage
Ocrael
Ocrael

1:52 They're starting to think like Gurdan Freemon

Vor 11 Tage
Ephraim Cullen
Ephraim Cullen

"One day, truly complex and intelligent agents will emerge." I hope not. Skynet will not be a picnic.

Vor 11 Tage
Anson Chan
Anson Chan

Im surprised they didn't trap them

Vor 11 Tage
Jamil Madanat
Jamil Madanat

I don't think we'll reach 'truly intelligent' .. I can't foresee designing an environment that mimics "real life"

Vor 11 Tage
YoseiHito
YoseiHito

@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.

Vor 10 Tage
Jamil Madanat
Jamil Madanat

@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?

Vor 10 Tage
YoseiHito
YoseiHito

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.

Vor 10 Tage
McQ
McQ

Nature inspires art. Not the other way around.

Vor 11 Tage
Colox
Colox

this video is very cute

Vor 11 Tage
JuN Bearded
JuN Bearded

Open AI + Boston Dynamics = we'll all die soon !

Vor 11 Tage
loYol
loYol

They deadass just made hide and seek bots

Vor 11 Tage
Weazel
Weazel

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.

Vor 11 Tage

Nächstes Video

Multi-Agent Hide and Seek

2:58

Lil Tjay - Hold On (Official Video)

4:07

Lil Tjay - Hold On (Official Video)

liltjayVEVO

Aufrufe 579 041

DeepMind - The Role of Multi-Agent Learning in Artificial Intelligence Research

1:01:10

SMAC: The StarCraft Multi-Agent Challenge

3:27

Système Multi Agent

24:51

Système Multi Agent

dzoulou vinci savitri DVS Informatique_ma_passion

Aufrufe 1

Counterfactual Multi-Agent Policy Gradients

48:43

Multi-agent Reinforcement Learning

11:37

I Tried Escaping A Bounty Hunter

14:35

I Tried Escaping A Bounty Hunter

BuzzFeed Multiplayer

Aufrufe 20

Google Pixel 4 (XL) - Mein Ersteindruck!

8:18

WhatsApp CHATS zwischen PAAREN!

10:11

WhatsApp CHATS zwischen PAAREN!

Gibt's Nicht

Aufrufe 110 844

CUM A LUAT FRATELE VOSTRU PERMISUL

24:42

I went AMD!! - Personal Rig Update Late 2019

18:17

I went AMD!! - Personal Rig Update Late 2019

Linus Tech Tips

Aufrufe 1 255 191