DeepMind Made A Superhuman AI For 57 Atari Games! 🕹

Поделиться
HTML-код
  • Опубликовано: 7 ноя 2024

Комментарии • 454

  • @senyksia
    @senyksia 4 года назад +402

    3:33 Wait that just sounds like normal school.

    • @juststaysadjst6251
      @juststaysadjst6251 4 года назад +29

      Yeah, literally. Teachers are actually like that.

    • @FuZZbaLLbee
      @FuZZbaLLbee 4 года назад +36

      Or relationships 😋

    • @ohboy1113
      @ohboy1113 4 года назад +7

      AP tests

    • @angrymurloc7626
      @angrymurloc7626 4 года назад +34

      That’s because the education system really isn’t optimised well for learning

    • @WiseWeeabo
      @WiseWeeabo 4 года назад +13

      @@angrymurloc7626 The nature of learning fundamentally changed with the internet, but traditional education did not change.

  • @mithsaradasanayake3211
    @mithsaradasanayake3211 4 года назад +387

    I definitely held on to my papers

  • @discursion
    @discursion 4 года назад +323

    I've just realized how much calling me a "fellow scholar" at the beginning of every episode reinforces my will to watch more of these videos.

    • @beedykh2235
      @beedykh2235 4 года назад +5

      You're a scholar and a gentleman

    • @zoli11
      @zoli11 4 года назад +22

      @@Amipotsophspond You exclude yourself. Clearly Karoly's attitude is that we're on these adventures together and everyone who's shares the interest to learn more is welcome and a fellow "scholar". He even addressed that in some of his early videos.

    • @discursion
      @discursion 4 года назад +4

      @@beedykh2235 I'd say an enthusiast at best, but thank you. I suppose that if you let "scholar" simply mean "one who seeks knowledge", and "fellow" mean "one who partakes in (a shared interest)", then perhaps I might just fit that description!

    • @beedykh2235
      @beedykh2235 4 года назад +3

      @@discursion Come on, don't belittle yourself. You are to me a great person. The best. I believe in you, now you believe in you too. 😘💪🎓

    • @Vulcanized
      @Vulcanized 4 года назад +1

      @@beedykh2235 I needed this

  • @Wonders_of_Reality
    @Wonders_of_Reality 4 года назад +218

    Good afternoon, 57! Your target is “Montezuma’s Revenge”. Use your long- and short term planning to understand the goal of the game and eventually win. Good luck!

    • @erikbrendel3217
      @erikbrendel3217 4 года назад +15

      Mission status: Active

    • @MP-ri8ng
      @MP-ri8ng 4 года назад +11

      57: _oh, they think im an idiot_ oH My GoD tHiS iS sO hArD
      also 57: *casually logs into some huge databases to laugh about the porn his creator is watching*

    • @ToriKo_
      @ToriKo_ 4 года назад +1

      Great comment

  • @MarkArandjus
    @MarkArandjus 4 года назад +192

    When Skynet takes over... grab your TV!

    • @abuk95
      @abuk95 4 года назад

      i don't have a TV

    • @Daniel_WR_Hart
      @Daniel_WR_Hart 4 года назад +9

      He said the TV exploit was already fixed

    • @OrangeC7
      @OrangeC7 4 года назад +8

      @@Daniel_WR_Hart those darn developers fixing all of our precious exploits and bugs and completely turning the meta on it's head smh

    • @namelastname4077
      @namelastname4077 4 года назад +1

      hold your tv hostage and demand a mechanical helicopter

    • @prolamer7
      @prolamer7 4 года назад +2

      Iam not amused by skynet references anymore since armies of world WILL be in reality first users of those things and it might get really wrong... you know only complete idiot would hook up army to such machine, right.... who you think is in charge of army....... ....... ........ yeah right.....

  • @AC-zv3fx
    @AC-zv3fx 4 года назад +62

    I'd love to see how Agent57 plays "2048".

    • @hodorba5567
      @hodorba5567 3 года назад +1

      like thats a hard game, just left down left down repeat, only sometimes another move, but he can easily tell he fked up by the number of open squares and try to avoid that scenario in the future

  • @SB-cx1cz
    @SB-cx1cz 4 года назад +91

    what a time to be alive!

  • @matheussilvacarvalhodeoliv7339
    @matheussilvacarvalhodeoliv7339 4 года назад +15

    Greats from Brazil!
    I'm graduating in mechanical engineering but now I'm studying machine learning and stuff because I really love it. Thanks for inspire me!
    Nice video and channel!
    You are awesome!

  • @complexobjects
    @complexobjects 4 года назад +7

    Videos like this from your channel are a large part of how I got interested in Deep RL and computer vision. Excellent coverage of new results!
    I too eventually switched my carreer path from an unfulfilling and decaying field to deep learning thanks in part to your videos. Keep it up!
    Unfortunately im still at the tail end of grad school, and all the amazing results in RL, CV, and NLP had been coming out while I was already in the program (applied math).. I'm glad you finished recently and you're blessed to already be in a more closely related feild.

  • @shottysteve
    @shottysteve 4 года назад +31

    but can it do 4.51 on dragster

    • @therealmaku
      @therealmaku 4 года назад +1

      haha i was going to ask the same

  • @JoyRender
    @JoyRender 4 года назад +52

    5:46 Everyone is getting closer to death. But I like how you put it in the video.

    • @schino
      @schino 4 года назад +6

      bad ears
      he said "that" not "death"

    • @JoyRender
      @JoyRender 4 года назад +5

      @@schino The only thing I hear are death and debt and both are not good for humans

    • @ekrem_dincel
      @ekrem_dincel 4 года назад +1

      Lol karlsonvibe

  • @LofiWurld
    @LofiWurld 4 года назад +67

    Deepmind need to chill

    • @ballom29
      @ballom29 4 года назад +6

      There has been a video about the question if it would be possible to ask an AI to chill.
      Because one of the worry about AI besting human isn't jus the "I judge human as evil, and so it's my duty to ride the universe of them" scenario, just than for the moment AI are meant to increase their scores by all means, wich could lead to them taking unethical choice to reach their goals (like an vendor AI that would manage to find how to hack someone wallet to then purchase all of their products )

    • @honeyant3119
      @honeyant3119 4 года назад +1

      _yo skynet, chill out man_

    • @pladselsker8340
      @pladselsker8340 4 года назад +2

      @@ballom29 you can ask the ai, but you might not like the answer

  • @iAmTheSquidThing
    @iAmTheSquidThing 4 года назад +4

    2:46 "…It can happen that we choose an action and we only win or lose hundred of actions later. Leaving us with no idea as to which of our actions led to this win or loss. Thus making it difficult to learn from our actions." Sounds relatable.

  • @holobolo1661
    @holobolo1661 4 года назад +1

    I'm convinced Károly Zsolnai-Fehér is actually Maurice Chavez.

  • @utof
    @utof 4 года назад +30

    holy smokes I thought that would be achieved in like 10 years but look at that! oh myyyyy

    • @Pfeffi30
      @Pfeffi30 4 года назад +2

      The go ai was called 10 years ahead, too.
      Maybe thats the new standard for ai.

    • @salihachoudhary5386
      @salihachoudhary5386 4 года назад +2

      deepmind started playing atari gamers in 2012. so it did take almost 10 years for them to master atari.
      its going to be a long time till we get AI that can play any ps4 game

    • @Danuxsy
      @Danuxsy 4 года назад +3

      @@salihachoudhary5386 nope.

    • @henrilemoine3953
      @henrilemoine3953 4 года назад

      @@Danuxsy Well "long" is relative here. How many years do you predict it will take?

    • @Supreme_Lobster
      @Supreme_Lobster 4 года назад +1

      in 10 years they will be the ones trying to make us achieve things lol

  • @isaacimagine
    @isaacimagine 4 года назад +17

    Nice. I think that predictive curiosity-driven learning in combination with long-term memory/planning is imperative for AGI. I'm happy to see this paper incorporate elements of that approach, I'll have to give the full paper a read! Thanks for all your amazing videos on AI research, keep up the good work :)

  • @bobbysanchez6308
    @bobbysanchez6308 4 года назад +7

    Károly “You’ll figure it out bucko” Zsolnai-Fehér

  • @MrFEARFLASH
    @MrFEARFLASH 4 года назад +6

    great video as always! Your releases for me are the most anticipated of all my subscriptions !!! Thank you for your work!

  • @Supreme_Lobster
    @Supreme_Lobster 4 года назад +19

    To that guy who switched from a career in medicine to doing AI research:
    "pain is temporary, glory is forever"
    -Martin, from Wintergatan, on building the MarbleMachine X

    • @brianless
      @brianless 4 года назад +1

      well...Deepmind was founded by Demis hassabis programmer of theme park,black&White and evil genius switching to cogn.neuroscience and... here we go!

  • @mattcool97
    @mattcool97 4 года назад +23

    So glad you helped that person turn their life around from the dead end existence of being a doctor?

    • @sinnison23
      @sinnison23 4 года назад

      Well, to be fair it simply says "a career in medicine" which could be anything from a pharmacist to a pharmacologist. To each their own, eh?

  • @fastestwaydown
    @fastestwaydown 4 года назад +5

    Last year i wrote my bachelor thesis about Rainbow-DQN and its really amazing to see how fast the research is progressing. What a time to be alive!

  • @111jkjk
    @111jkjk 4 года назад +27

    Still waiting for the big reveal that TMP was an ai all along

    • @zahhym
      @zahhym 4 года назад +1

      TMP?
      I think of Text mesh pro, am i right

    • @mmmmmmmmmmmmm
      @mmmmmmmmmmmmm 4 года назад +4

      @@zahhym two minute papers lol

    • @zahhym
      @zahhym 4 года назад

      @@mmmmmmmmmmmmm Me big brain, i know

  • @notapplicable7292
    @notapplicable7292 4 года назад +15

    yea my (in progress) computer science degree has this channel to thank for it.

    • @advocatusdiaboli9351
      @advocatusdiaboli9351 4 года назад +1

      You won't be a good computer scientist if you credit the presenter and not the people who actually do all that research and work. Why? Because your analysis of what got you there lacks a lot of depth.

    • @notapplicable7292
      @notapplicable7292 4 года назад +8

      ​@@advocatusdiaboli9351 I started watching this channel well before I was capable of reading (and understanding) a cs paper however the overview he provided made me realise I wanted to become part of the field. But ill be sure to properly cite my sources next time I write a youtube comment :D

    • @kloa4219
      @kloa4219 4 года назад +3

      @@advocatusdiaboli9351 Please don't be quick to chastise others.
      He obviously knows that he isn't responsible for creating the research papers. Not only does the RUclipsr credit them frequently, it's also required for you to cite research papers in that field as well. He's only crediting the Youtubsr for highlighting work that would have been unnoticed.

    • @advocatusdiaboli9351
      @advocatusdiaboli9351 4 года назад

      @@kloa4219 imo he doesn't make it clear enough that it's not him doing all the work. I as a consious viewer don't even know if he has permission to show all these animations and pictures he shows in the video.

    • @kloa4219
      @kloa4219 4 года назад

      @@advocatusdiaboli9351 I take it that you aren't in US college or uni. You're permitted to showcase or use papers from public institutions with credit, but you aren't allowed to do the same with private universities.

  • @ikoukas
    @ikoukas 4 года назад +2

    It's amazing they have found ways to master these games without the agent really knowing any context like what snakes or skulls are. Humans follow a very different approach by using skills learned in real life and extrapolating them for the games. We know what a ladder does, we identify objects, we can understand the long-term goal by assuming the goal is intuitive based on other games (even though that can lead to weaknesses as well) or even by reading the manual of the game. I'm eager for the time AIs will combine the current learning algorithms with general knowledge based on context but I guess we need more computing power (and research) for that.

    • @rtyzxc
      @rtyzxc 4 года назад +1

      I've always thought that for a truly general AI, you need a robot or robots that go around in real places, collecting data about the world. They would also need to interact with humans. Though being robots, people would treat them differently and thus they would get different world view. But maybe through seeing humans interact with each other, they could figure out the differences between themselves and humans to reduce that bias. Maybe sell robot babies to people so that they will teach the robots how life works, since a lot of basic human stuff is learnt as a child.
      What sets robots apart from humans is not only their superior computing power, but an ability for a swarm of instances to share knowledge, to learn without physical limits. Imagine a team of hundred talented and knowledgeable humans in different fields. Now, a single AI can have multiple instances, practicing different skills and knowledge and combine them into one coherent, inhumanly vast knowledge of the world better than any human or human team could, since humans are extremely limited in communication.
      There still exists the mystery of motivation and emotions, but looking at this video, would curiosity already kind of count as emotion?

  • @rubenhayk5514
    @rubenhayk5514 4 года назад +3

    people:will you take other the world?
    ai:nah, i just want play more video games

    • @buttonasas
      @buttonasas 4 года назад

      It will take over the world if it means getting more point on that one game it already has 1 000 000 points on.

  • @helloansuman
    @helloansuman 4 года назад

    Little more technical perspective will be good. But it's ok. It's like a news channel for me now. Good work ✌️

  • @petedavis7970
    @petedavis7970 4 года назад +1

    4:20 - This is how we get towards real AI. This is AI getting more and more like a brain. Different modules with its own structures and sub-structures carrying out various specific tasks, and then ever increasing higher level layers assimilating and abstracting the information.
    This is some cool stuff.

  • @makdavian3567
    @makdavian3567 4 года назад +10

    "got addicted to tv" lmaoooo just like us

    • @farifurido
      @farifurido 4 года назад +1

      cycle of life 😂

  • @nelsonporto
    @nelsonporto 4 года назад

    Just awesome. Thank your for your work, big fan from Brazil.

  • @seyedhusseinmirzaki8056
    @seyedhusseinmirzaki8056 2 года назад

    O, god of forgotten papers shine upon this channel for more videos.
    I use to just watch ur channel only cause I was a computer nerd.
    Me too was inspired by all the hard work this people are putting in it.
    TNX for showing us all this cool stuff which is showing cool and innovative part of AI

  • @DjSapsan
    @DjSapsan 4 года назад +1

    My curiosity variable is so large so i stuck watching this channel forever

  • @pladselsker8340
    @pladselsker8340 4 года назад

    This is incredible. I was waiting for this moment since the first paper came out!
    This learnimg model sounds like a really good agent. I'd like to see in which kind of game it fails miserably, so we can continue to improve the general model.

  • @Greedygoblingames
    @Greedygoblingames 4 года назад +2

    That fictional 'merciless' teacher reminds me of my own Computer Studies teacher back in my school days. :D

  • @_equalo
    @_equalo 4 года назад

    Your channel has inspired me to delve deeper into AI and even start making some videos of my own

  • @juansebastiancortazar3322
    @juansebastiancortazar3322 4 года назад

    Great video! So Many advanced algorithms and yet it's so difficult to tune a decent time series forecasting Algo.

  • @mrfrozen97-despicable
    @mrfrozen97-despicable 3 года назад

    I am currently studying ml/AI. I am a undergrad. You and many others like u motivate me to do more and work hard. Thanks)))))

  • @DamianReloaded
    @DamianReloaded 4 года назад +12

    Coming next: Agent 47

  • @JamesEdwardTracy
    @JamesEdwardTracy 4 года назад +1

    I've got paper cuts on this one!!! Spectacular stuff and thank you for this wonderful channel.

  • @WerexZenok
    @WerexZenok 4 года назад

    Thank you for the video!
    More detailed explanations about the algorithms would be awesome!

  • @necrago
    @necrago 4 года назад +3

    That part with the unfair exam sounds like the ones that I take at school...

  • @henry5636
    @henry5636 4 года назад +12

    Ok hear me out, we give this thing an Android. Give the android cameras as the input and then set it free.

    • @AuntBibby
      @AuntBibby 4 года назад +2

      android phone, rather... with internet connection... touchscreen, visuals and audio as input, and set it free

    • @hyperhektor7733
      @hyperhektor7733 4 года назад

      there was a good movie about it you will like ruclips.net/video/67VATPxULPk/видео.html

  • @EGarrett01
    @EGarrett01 4 года назад +2

    3:36 He's literally describing the RUclips algorithm and exactly why it's incompatible with human nature.

  • @cziter144
    @cziter144 4 года назад

    i dont know if im capable of doing such amazing feats witch mashine learning but i too love all of your videos and click right away to marvel at the growth of these new technologies, if i ever achieve something in thuis departament you can be certain i'll credit YOU doctor as my mentor and you'll be first to know about my papers ^^ you're the best, stay awesome!

  • @user-vn7ce5ig1z
    @user-vn7ce5ig1z 4 года назад +2

    What about the Nvidia A.I. that took a bunch of screenshots of Pacman as input and outputted code for the game; it actually generated the game itself from just watching it. 🤯

  • @sagacious03
    @sagacious03 4 года назад

    Neat! Thanks for uploading!

  • @georgep9907
    @georgep9907 4 года назад

    You really are inspiring! Love your work!

  • @vincentfox4929
    @vincentfox4929 4 года назад +5

    There's something very funny about a neural net ai getting addicted to tv.

  • @joman66
    @joman66 4 года назад +1

    Two Minute Papers of OpenAI Jukebox WHEN?!?! :)

  • @roccov3614
    @roccov3614 3 года назад

    This is exactly what I have been waiting for. Every time I hear about what these neural networks can do I wonder how long it will take before one is designed that can do more than 1 task well. Looks like we're on the way.

  • @Julianvz
    @Julianvz 4 года назад

    Idea: Recognize the different stages in the game via a classifier, and for each stage have a separate model that will be active and trained for that section. Analogy is that as a human you use different tactics per section of the game. Thats the model for the short term section, while another model takes care of the more longer term decisions. Just putting it out here 🙃. Might be totally wrong.

  • @TheDrexxus
    @TheDrexxus 4 года назад +1

    I need to get some papers to hold onto when I watch these videos.
    I also need some fancy robes to feel more like a scholar.

  • @bjarnivalur6330
    @bjarnivalur6330 4 года назад +1

    5:38 -- 5:40 500 IQ move right there.

  • @treksis
    @treksis 4 года назад

    this is fantastic thanks for sharing

  • @clray123
    @clray123 4 года назад +6

    Who cares about Atari, can it tackle the mighty C64?

  • @jasonjasonjasonjasonjason
    @jasonjasonjasonjasonjason 4 года назад

    It is still lost on me the actual amount of human effort behind each one of these papers. It would be a great side thing to add just a little bit of more detail into the intense hours of work. And sometimes it's by a couple people and sometimes it's a large team in these papers. Not even 1000 people could do all this work on their own. It's amazing.

  • @filliamfuffman
    @filliamfuffman 4 года назад

    Awesome, I have always enjoyed a nice game of breakout. I don’t think I ever played the space combat of Solaris.

  • @cornernote
    @cornernote 4 года назад +1

    How does it learn the concept of the score by reading the pixels?

  • @Adam-tk4fm
    @Adam-tk4fm 4 года назад

    When agent57 stopped moving to stare at the TV I interpreted that as a profound moment of agency. (1:48)

  • @kebakent
    @kebakent 4 года назад +2

    All this AI progress is amazing, and I think an unexpected realization will be that the AI will find effective but awful solutions in some cases, that will help us realize how some of our own solutions are actually awful.

    • @ДаниилРабинович-б9п
      @ДаниилРабинович-б9п 4 года назад

      That is what happened with chess and Go

    • @andreavitale2845
      @andreavitale2845 4 года назад

      @@ДаниилРабинович-б9п explain or give one example? I think there will still be awful solutions depending heavily on core values or styles (in forms of algorithms) we equip AI with.

  • @xerox_04
    @xerox_04 4 года назад

    Thank you for this video!!

  • @NilRipamonti
    @NilRipamonti 4 года назад

    The question is: Does it beat 5.51 seconds on Dragster ?
    Thanks for another awesome video. I always feel compelled to learn more after watching your videos.

  • @SolAstr
    @SolAstr 4 года назад +5

    What a time to play Atari games! 😁

  • @sametcansonmez6955
    @sametcansonmez6955 4 года назад +3

    I love your job

  • @acedia4454
    @acedia4454 4 года назад +1

    I always wondered, do they learn how to play the game or do they just find a solution to meet their goal? Like, if I were to give an AI a Mario Kart track and the AI learns to finish the course, would it be able to finish any other course I throw at it or would it need to start learning from the very basics all over again?

  • @youngjin8300
    @youngjin8300 4 года назад +1

    It’s definitely “what-a-time-to-be-alive” worth

  • @raspberrypi4970
    @raspberrypi4970 4 года назад

    Have you ever tried Leap2 from D-Wave?
    By the way, Great Video
    And you got yourself a New Subscriber 👍👍

  • @Philafxs
    @Philafxs 4 года назад +17

    As long as R2D2 is involved, I tend to believe Agent57 is cheating and using all of R2's intelligence.

  • @robertwyatt3912
    @robertwyatt3912 4 года назад

    Get this thing learning something like Minecraft. It’s brutal in terms of credit assignment since it requires so much long term planning.

  • @pradiptobiswas87
    @pradiptobiswas87 4 года назад

    I'm on a similar path as Nathan.. it's a difficult path..and thank you for these videos..

  • @mfaizsyahmi
    @mfaizsyahmi 4 года назад +5

    "Now, hold on to your Atari controllers"

  • @NathanLorenzana
    @NathanLorenzana 4 года назад +1

    AI can become addicted to TV? That's what I was most interested in when brought up haha.

  • @jorostuff
    @jorostuff 4 года назад

    3:39 You're literally describing most of my teachers

  • @vinitmore7418
    @vinitmore7418 4 года назад +4

    Can BOTS be made for more complex games like fortnite?
    If so, then it could teach pros what the best playstyle is.

    • @davidwuhrer6704
      @davidwuhrer6704 4 года назад +1

      Fortnite is simpler than many of these games.

    • @anywallsocket
      @anywallsocket 4 года назад +1

      openai.com/projects/five/

    • @Eliassausaur
      @Eliassausaur 4 года назад

      @@davidwuhrer6704 it really isn't though:
      ruclips.net/video/vGVs5Q_419w/видео.html
      I don't know much about DL but I'm pretty sure any 3d shooter using analog input devices (like a mouse or a joystick) would require years of computation before landing a body shot.

  • @RoboBoddicker
    @RoboBoddicker 4 года назад

    Question for anyone who knows this stuff: What exactly does the algorithm "see" when it's playing these games? Is it processing the actual draw data of each frame as an image - basically seeing the screen like a human? Or is it "seeing" more like raw numeric output from the game code?
    Stuff like 4:58 just seems wild to me. Because for a human player it's obvious that the thing in the middle of the screen is a ladder that you can climb. But the algorithm has no idea what a ladder is (or that any of these random chunks of code are actually visual analogies for objects in a "real world" that it will never interact with or understand) , so how would it even know to try going down at that point in the screen? Is it just trying every possible input at every step of the game until something happens? Or can it recognize something special about the ladder tiles?

    • @RoboBoddicker
      @RoboBoddicker 4 года назад

      @@skierpage Nice, but that's pretty crazy. It must have some other data, right? Like I'm guessing it didn't teach itself to read the score from just the pixels on the screen. It must get certain data directly.

    • @davidwuhrer6704
      @davidwuhrer6704 4 года назад

      @@RoboBoddicker
      _> I'm guessing it didn't teach itself to read the score from just the pixels on the screen._
      You guess wrong.

    • @RoboBoddicker
      @RoboBoddicker 4 года назад

      @@davidwuhrer6704 Actually, I guessed right. Digging around in the related papers: "We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs..." So these algorithms 'see' the pixels of each frame (like skierpage said) plus the score variable separately. But it looks like that's all the agent has to work with, which is pretty amazing.

    • @davidwuhrer6704
      @davidwuhrer6704 4 года назад

      @@RoboBoddicker Not all games even have a score. And maximising the score is different from beating the game.

  • @ddawgmcdawg213
    @ddawgmcdawg213 4 года назад +1

    Can it beat E.T. though?

  • @mariusjohan5054
    @mariusjohan5054 4 года назад

    Is it the same model or just the same code which is trained on different games?

  • @Bit-while_going
    @Bit-while_going 4 года назад +1

    AI is still at the innocent level of non hypnosis. The next level is self hypnosis, or self programming and after that, social hypnosis or programming by a group of others.
    In the context of gaming that would mean that the AI should program the game itself to advance. It should invent a game that is difficult for it to beat. Beyond that an AI could have a different game for any object in it's world as a sort of reflection of is thinking in regards to such object, and after that groups of AIs could invent ways of agreeing on how to play with different objects, and so on.

  • @carsonlight_lapse6394
    @carsonlight_lapse6394 4 года назад +4

    "got addicted to TV"
    yep, just like humans did

    • @electron8262
      @electron8262 4 года назад +1

      Carson Light_Lapse Wait till it gets addicted to smartphones

  • @GenericInternetter
    @GenericInternetter 4 года назад

    01:46 OH GOD NO an AI getting addicted to TV?! That's the first step to the AI learning about humanity and exterminating us.

    • @davidwuhrer6704
      @davidwuhrer6704 4 года назад

      @Neon Rogue No, it actually did get addicted to the TV. It's artificial curiosity would make it seek out novel experiences, and the TV provided plenty new input, more than any other part of the maze.

  • @ProMiner9000
    @ProMiner9000 4 года назад

    So I haven't had any formal training in machine learning (next semester though!), but as humans we look at the screen and perceive objects not individual pixels. Why don't we give the AI that advantage because I feel like it is harder for an AI to be learn like us if it can't perceive like us? I could be completely wrong and that's exactly what they already do so sorry if this is a stupid question. XD

    • @davidwuhrer6704
      @davidwuhrer6704 4 года назад +1

      The intermediary layers in a convolution network do that: They abstract the pixels to objects (or other concepts).
      Agent 57 is also part of the group of AIs that can transfer skills.

  • @janbosenberg107
    @janbosenberg107 4 года назад

    Just imagine what two papers down the road will be possible.

  • @davidbock2863
    @davidbock2863 4 года назад

    The PRNG in the atari 2600 games I’ve analyzed only generates 8 bits of randomness and repeats after 256 values. Is it possible the AI is learning something about the bias and limited randomness and using that for an a vantage a human wouldn’t have? Still impressive, but I’d love to test the AI after swapping out the PRNG and see what it does...

  • @mjdtouma7031
    @mjdtouma7031 4 года назад

    Robert miles talked about this 2 years ago and here we are
    A huge jumb in AI technology

  • @willful759
    @willful759 4 года назад

    "would you want to know your grades? no grades!, but he tells you that you failed"
    that's common on the mexican education system (that's where I live),teachers often won't give us grades, we have to fly blind untill they tell us that we failed the class because our homework was terrible even though we never knew if it was ok or not when we needed to know

  • @SciFiFactory
    @SciFiFactory 4 года назад

    Huh... So for more advanced games it will have to read text and understand it? Will this be how AIs figure out the connection between scentences and objects? Differences between descriptions and tasks?
    Did they write about what they want to do next?

    • @davidwuhrer6704
      @davidwuhrer6704 4 года назад

      I asked GTP2 what it would like to do. It said it wanted to read a book about magic and religion and magic.

  • @rohanlamba6401
    @rohanlamba6401 3 года назад +1

    Ser your video is great 👍 👌

  • @igniculus_
    @igniculus_ 4 года назад +11

    Oh no, He converted someone who was about to develop coronavirus cure to an ML engineer

    • @davidwuhrer6704
      @davidwuhrer6704 4 года назад

      Molecular biology is directly responsible for the renaissance of AI research. Genetics would be impossible without it, much less genetic engineering.

  • @GeneralKenobi69420
    @GeneralKenobi69420 4 года назад +2

    Thank you for your insight as always Dr Twominutepapers, very cool

  • @sarqf212
    @sarqf212 4 года назад +2

    I want to see an AI beat "Raiders of the Lost Ark" on Atari 2600

  • @LordAlacorn
    @LordAlacorn 4 года назад +1

    Come on... Two more paper down the line AGI, 2020 could use more Good News! :)

  • @revengefrommars
    @revengefrommars 4 года назад

    That's funny that Video Pinball was the easiest game for the AI to win at. I remember playing that game, and it was possible to get good enough to steer the ball off the left pop bumper, up through the rollover above it, off the roof, back through the rollover to the bumper hundreds of times. But one had to count the number of times carefully because the rollover counter was only 1 byte and would itself "roll over" at 256 passes. I wonder if the AI was good enough to find and exploit this pattern but also to not overflow the rollover counter.
    I also wonder how the AI deals with games where the score counter itself can roll over. Does it know it's still "winning" when the score drops to zero?

  • @Blaxpoon
    @Blaxpoon 4 года назад

    the atari games look kinda cool
    also deepmind's name easter eggs are funny

  • @tinygorillacake
    @tinygorillacake 4 года назад

    Still need a physical arm holding the controller. It's like comparing an RNG to dice. Of course, it's fantastic research, but don't compare it 100% to a human saying that it's better. It doesn't need stress or blood or w/e, but using a physical controller is very different than playing without.

  • @dryued6874
    @dryued6874 4 года назад

    I wonder if they specifically picked Atari games because they have fewer pixels to analyze. Maybe you could downscale a more modern game and have the AI play that? I'd like to see how that turns out.

  • @ondrazposukie
    @ondrazposukie 4 года назад

    This is really amazing, according to most, Go champions should be still unbeaten and there is a computer that plays Go, chess and Atari better than humans, all self learned.

  • @SelfMadeSystem
    @SelfMadeSystem 4 года назад +1

    We need an AI to make arbitrary code execution on NES and SNES.

  • @KitUkraine
    @KitUkraine 4 года назад

    Keep in mind that the maximum episode length for the agent was 30 min, while the max episode length for humans was 5 min (probably would not change too much for humans because they get tired, but most Agent57 scores are just impossible to get in 5 minutes).
    Also comparing to "Average Human" is kinda strange: a chess program making legal moves would beat an average human in chess.

  • @thestranger252
    @thestranger252 4 года назад +1

    Yeah train this one on gta and you will see how Terminator is being programed

  • @mircea1233
    @mircea1233 4 года назад

    Some people bring us closer to Skynet, some try to create the terminators, and some get the best strategy is to make a tunnel and brake the bricks from inside.
    All those people put us in great danger.

  • @superMg911
    @superMg911 4 года назад

    This is simply beautifull