Multi-Agent Hide and Seek

čas přidán 17. 09. 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: openai.com/blog/emergent-tool-use/

Komentáře

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

  • Remember when humans use to play hide and seek?

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

  • How do I learn to do this?

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

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

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

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

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

    • @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.

    • ​ 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.

    • 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

  • multi.ai

  • And this my gamers is the *recommended page*

  • Uncomfortable

  • Is that a game!?!?!?!?!

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

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

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

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

  • スゲェ…

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

  • SkyNet liked this video

  • beautiful

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

  • 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.

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

  • bomba kimi

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

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

  • AQUI É BR VAI BRASIL TEMOS A AMAZÔNIA

  • 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.

  • This is witchcraft! WOW!

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

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

  • 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

  • Welcome to the Aperture Science computer-aided enrichment center.

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

  • oh yeah, this is big brain thime

  • Can someone make this a game

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

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

  • Im surprised they didn't trap them

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

    • @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.

    • @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?

    • 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.

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

  • Nature inspires art. Not the other way around.

  • this video is very cute

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

  • They deadass just made hide and seek bots

  • 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.

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

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

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

  • Yeahhhh We're teaching them to kill us in futute.

  • Those faces adorable .

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

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

  • Parkour!

  • Andrew Yang warned us about this. #YangGang2020

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

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

  • is this deep learning?

  • good to see they evolved in defense not offense. be worried when they start boxing in the seekers first and free to walk around.

  • Whooooooooaaaaaaaahhh