Multi-Agent Hide and Seek

  • Published on Sep 17, 2019
  • 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:
  • Science & TechnologyScience & Technology

Comments • 2 579

  • HackTor
    HackTor Hour ago

    Remember when humans use to play hide and seek?

  • Harry
    Harry 2 hours ago

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

  • vijay vittal
    vijay vittal 4 hours ago

    How do I learn to do this?

  • DuoBV Channel
    DuoBV Channel 9 hours ago

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

  • mohammed bilal kolkar
    mohammed bilal kolkar 14 hours ago

    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 21 hour ago +1

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

  • Loop
    Loop Day ago

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

    • Loop
      Loop 14 hours ago

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

    • John DC
      John DC 15 hours ago

      @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
      Loop 15 hours ago

      ​ 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 15 hours ago

      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 days ago

  • Harry
    Harry 2 days ago

    And this my gamers is the *recommended page*

  • Late night talk show with the Bronson


  • mr. grootex
    mr. grootex 3 days ago

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

  • João Ramon Gomes Da Silva

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

  • 4ammofo
    4ammofo 3 days ago

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

  • Bratteries and Snignals

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

  • ChuckNorris100000
    ChuckNorris100000 4 days ago

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

  • kiko synth
    kiko synth 4 days ago


  • Next Gen Games
    Next Gen Games 4 days ago +1

    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

    SkyNet liked this video

  • Kick Lee
    Kick Lee 6 days ago


    PARALLEL UNIVERSE 6 days ago

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

  • Xuezhou Zhang
    Xuezhou Zhang 7 days ago +1

    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 days ago

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

  • Azeri Lyrics
    Azeri Lyrics 7 days ago

    bomba kimi

  • YoseiHito
    YoseiHito 7 days ago

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

  • Gustav Isak Abrahamsson

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

    EL EXTERMINADOR 8 days ago


  • WulfCry
    WulfCry 8 days ago

    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 days ago

    This is witchcraft! WOW!

  • Football addicts
    Football addicts 8 days ago

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

  • Bhuvanesh s.k
    Bhuvanesh s.k 8 days ago

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

  • Bhuvanesh s.k
    Bhuvanesh s.k 8 days ago

    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 days ago

    Welcome to the Aperture Science computer-aided enrichment center.

  • Leeroy Jenkins
    Leeroy Jenkins 8 days ago

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

  • David Baumann
    David Baumann 8 days ago

    oh yeah, this is big brain thime

  • Bloodcrow 100
    Bloodcrow 100 8 days ago

    Can someone make this a game

  • Ocrael
    Ocrael 8 days ago

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

  • Ephraim Cullen
    Ephraim Cullen 9 days ago +1

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

  • Anson Chan
    Anson Chan 9 days ago

    Im surprised they didn't trap them

  • Jamil Madanat
    Jamil Madanat 9 days ago

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

    • YoseiHito
      YoseiHito 7 days ago

      @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 days ago

      @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
      YoseiHito 7 days ago

      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 days ago

    Ultron, come and teach these two little ones how to play hide and seek

  • McQ
    McQ 9 days ago

    Nature inspires art. Not the other way around.

  • Colox
    Colox 9 days ago

    this video is very cute

  • JuN Bearded
    JuN Bearded 9 days ago

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

  • loYol
    loYol 9 days ago

    They deadass just made hide and seek bots

  • Weazel
    Weazel 9 days ago

    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 days ago

    2:49 ... and wipe humanity the fuck out.

  • Grigor Yeghiazaryan
    Grigor Yeghiazaryan 9 days ago

    Elon, be careful not to loose them, they can hide from you 😁

  • FieldSweeper
    FieldSweeper 9 days ago

    see no matter what rules you are given in a game. people will always try to break them hahaha

  • #theofficial_ kami
    #theofficial_ kami 9 days ago

    We're teaching them to kill us in futute.

    USBEN 9 days ago

    Those faces adorable .

  • a little boy
    a little boy 9 days ago

    "This works by algorithms." No way, really? A little more information would be appreciated.

  • nineof8
    nineof8 9 days ago

    OpenAI is a precursor to the simulation we'll find ourselves in

  • Yahya Jaber
    Yahya Jaber 9 days ago


  • wafflepiepancake
    wafflepiepancake 10 days ago

    Andrew Yang warned us about this. #YangGang2020

  • hotkulboi77
    hotkulboi77 10 days ago +1

    *meanwhile dumb ass muslims want to take this civilization 1000 of years back*

  • SeungHyun
    SeungHyun 10 days ago

    Trump: *builds wall*
    Mexican surfer : "hola amigo"

  • Keylo moon
    Keylo moon 10 days ago

    is this deep learning?

  • Glamour Window Tinting

    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 days ago


  • Daniel
    Daniel 10 days ago

    If this was a game I'd play it.