Multi-Agent Hide and Seek

コメント数

  1. Caleb Cruz

    Caleb Cruz時間 前

    Dead by daylight really downgraded

  2. Im On Da Web

    Im On Da Web3 時間 前

    Dang I wish normal people could run this simulation

  3. Agitated

    Agitated3 時間 前

    Fake news

  4. MartyMacaroni

    MartyMacaroni3 時間 前

    Yo this game looks sick is it on steam?

  5. Don’t touch my phone Gamer

    Don’t touch my phone Gamer3 時間 前

    Ai really be learning how to glitch

  6. Jordan Bigby

    Jordan Bigby8 時間 前

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

  7. zbobz12

    zbobz129 時間 前

    That's freaking cool

  8. dxxPacmanxxb

    dxxPacmanxxb9 時間 前

    This is not in-depth enouuugh

  9. xX_Kjcomputer_Xx

    xX_Kjcomputer_Xx15 時間 前

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

  10. The Other Side

    The Other Side17 時間 前

    *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.*

  11. Pseudo X

    Pseudo X日 前

    He attacc He protecc but most importantly He surfs in buccs

  12. Lucas R

    Lucas R日 前

    So basically it’s slavery with extra steps

  13. Dolank

    Dolank日 前

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

  14. Lucas R

    Lucas R日 前

    IKR

  15. SMART THOUGHTS

    SMART THOUGHTS日 前

    Better . Far far better

  16. i love love song

    i love love song日 前

    Tech them to speak

  17. Shivam Dhoot

    Shivam Dhoot日 前

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

  18. SpaceDave1337

    SpaceDave1337日 前

    You should make this a Videogame somehow

  19. Mr. MindReader

    Mr. MindReader日 前

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

  20. gangster gandalf

    gangster gandalf2 日 前

    Im surprised they didnt lock in the seekers

  21. fl00fydragon

    fl00fydragon2 日 前

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

  22. The Potato

    The Potato2 日 前

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

  23. HackTor

    HackTor2 日 前

    Remember when humans use to play hide and seek?

  24. Harry

    Harry2 日 前

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

  25. vijay vittal

    vijay vittal2 日 前

    How do I learn to do this?

  26. DuoBV Channel

    DuoBV Channel3 日 前

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

  27. mb k

    mb k3 日 前

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

  28. Ee Cheng LEE

    Ee Cheng LEE3 日 前

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

  29. Loop

    Loop4 日 前

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

  30. Loop

    Loop3 日 前

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

  31. John DC

    John DC3 日 前

    @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.

  32. Loop

    Loop3 日 前

    ​ 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.

  33. John DC

    John DC3 日 前

    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

  34. Igor Gabrielan

    Igor Gabrielan5 日 前

    multi.ai

  35. Harry

    Harry5 日 前

    And this my gamers is the *recommended page*

  36. Late night talk show with the Bronson

    Late night talk show with the Bronson5 日 前

    Uncomfortable

  37. mr. grootex

    mr. grootex5 日 前

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

  38. João Ramon Gomes Da Silva

    João Ramon Gomes Da Silva6 日 前

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

  39. 4ammofo

    4ammofo6 日 前

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

  40. Bratteries and Snignals

    Bratteries and Snignals6 日 前

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

  41. ChuckNorris100000

    ChuckNorris1000006 日 前

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

  42. kiko synth

    kiko synth7 日 前

    スゲェ…

  43. Next Gen Games

    Next Gen Games7 日 前

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

  44. Ganymede, Jupiter III

    Ganymede, Jupiter III8 日 前

    SkyNet liked this video

  45. Kick Lee

    Kick Lee9 日 前

    beautiful

  46. PARALLEL UNIVERSE

    PARALLEL UNIVERSE9 日 前

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

  47. Xuezhou Zhang

    Xuezhou Zhang9 日 前

    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.

  48. Jay Sukumalchan

    Jay Sukumalchan10 日 前

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

  49. Azeri Lyrics

    Azeri Lyrics10 日 前

    bomba kimi

  50. YoseiHito

    YoseiHito10 日 前

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

  51. Gustav Isak Abrahamsson

    Gustav Isak Abrahamsson10 日 前

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

  52. EL EXTERMINADOR

    EL EXTERMINADOR11 日 前

    AQUI É BR VAI BRASIL TEMOS A AMAZÔNIA

  53. WulfCry

    WulfCry11 日 前

    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.

  54. Jack Napier

    Jack Napier11 日 前

    This is witchcraft! WOW!

  55. Football addicts

    Football addicts11 日 前

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

  56. Bhuvanesh s.k

    Bhuvanesh s.k11 日 前

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

  57. Bhuvanesh s.k

    Bhuvanesh s.k11 日 前

    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

  58. Abe Alexander

    Abe Alexander11 日 前

    Welcome to the Aperture Science computer-aided enrichment center.

  59. Leeroy Jenkins

    Leeroy Jenkins11 日 前

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

  60. David Baumann

    David Baumann11 日 前

    oh yeah, this is big brain thime

  61. Bloodcrow 100

    Bloodcrow 10011 日 前

    Can someone make this a game

  62. Ocrael

    Ocrael11 日 前

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

  63. Ephraim Cullen

    Ephraim Cullen11 日 前

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

  64. Anson Chan

    Anson Chan11 日 前

    Im surprised they didn't trap them

  65. Jamil Madanat

    Jamil Madanat12 日 前

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

  66. YoseiHito

    YoseiHito10 日 前

    @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.

  67. Jamil Madanat

    Jamil Madanat10 日 前

    @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?

  68. YoseiHito

    YoseiHito10 日 前

    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.