I Trained an A.I to Train A.I (Deep Reinforcement Learning)

Поделиться
HTML-код
  • Опубликовано: 15 ноя 2024

Комментарии • 141

  • @Zuzelo
    @Zuzelo  Год назад +33

    Like and Subscribe if your first round isn't too dynamic and quite short either!

  • @KingKhiGaming
    @KingKhiGaming Год назад +202

    Just like my own childhood thank you so much

  • @Mrdashell
    @Mrdashell 11 месяцев назад +22

    Now imagine if you added a mom ai that's job was to prevent dad ai from slapping the silly out of little pogo

    • @Zuzelo
      @Zuzelo  11 месяцев назад +5

      xD

    • @NecyarUnáty
      @NecyarUnáty 6 месяцев назад +1

      It can go on eternally, adding more and more pogos

    • @nw5922
      @nw5922 Месяц назад

      I want the mom ai to be a mormon, start a family of 8, go viral, and then go to jail.

  • @Depth_.
    @Depth_. Год назад +24

    I think only you could think of this, another classic

  • @maxiawesomekid899
    @maxiawesomekid899 Год назад +35

    He was to lazy to make an agonizingly complicated ai so instead he made an even more agonizingly complicated ai to teach slightly less agonizingly complicated ai s

    • @Zuzelo
      @Zuzelo  Год назад +6

      hmmm... now that you put it like that, perhaps it was not the most efficient solution xD

  • @changsookwak4636
    @changsookwak4636 4 месяца назад +4

    The Ai dad is like a Russian that smacks the spider out of the Ai child xD

  • @tranquilclaws8470
    @tranquilclaws8470 Год назад +39

    One idea for AI learning that I thought up while watching a Trackmania video was having the AI work towards an ultimate goal but also setting its own sub-goals that half of the instances would work towards. After achieving some success with the sub-goal, this split AI would then be evaluated by the main goal again. This would allow the AI to innovate its strategy and explore new avenues to reach unorthodox ways of accomplishing the objective that only being rewarded for working toward the ultimate goal might never reveal.
    In the Trackmania example, the AI refused to drift around corners, as drifting was thought to be a waste of time. The AI was given the goal of drifting as much as possible instead of getting a good time on the track. After a few successful drifting iterations were completed, the new drifting AI was again measured by the track completion time goal. It got a better goal than before because it could now properly incorporate drifting to get around corners faster.

    • @Zuzelo
      @Zuzelo  Год назад +16

      Indeed, dividing the training in this way might help with avoiding getting stuck in local min/max.
      Designing the reward system usually is half the work :D
      Might be worth trying it out

    • @howuhh8960
      @howuhh8960 Год назад +1

      it is known as hierarchical rl, usually it does not work and very unstable in practice, so I would advise to use something else, like better exploration strategies (beyond simple gaussian noise)

    • @tranquilclaws8470
      @tranquilclaws8470 Год назад +2

      @@howuhh8960 Sounds fair. I suppose it only worked in Trackmania because the coder of the AI knew that drifting was more efficient than driving straight around corners and pointed the AI in the right direction.

    • @JohnDoe-qm6ub
      @JohnDoe-qm6ub Год назад +1

      Pardon my ignorance, but what is the difference between that and just giving a +1 reward to drifting and -1 reward for time taken?

    • @tranquilclaws8470
      @tranquilclaws8470 Год назад +1

      @@JohnDoe-qm6ub You would be negating learning how to drift with the time wasted overcoming the hurdle of learning how to drift. Really it would be distance x proportion of time spent drifting becoming the reward that would get the AI to drift more.

  • @kaunghlamyat
    @kaunghlamyat Год назад +31

    Trainign an ai to train an ai isn't very good idea as it seemed to.
    its like *trainign a failure to train a failure*

    • @Zuzelo
      @Zuzelo  Год назад +13

      I don't see what could go wrong

    • @kaunghlamyat
      @kaunghlamyat Год назад +2

      @@Zuzelo neither am I but lol

  • @ezbooksmarketing5898
    @ezbooksmarketing5898 Год назад +7

    New video in September 9 2069: "I trained an AI to train humans"

    • @Zuzelo
      @Zuzelo  Год назад

      Pogo for the 2069 President!

  • @louisisson7946
    @louisisson7946 Год назад +3

    Can you make a dodge ball
    A. I. Learning “game”?

  • @timer1238
    @timer1238 Год назад +18

    I have an idea for even more functions for the AI war
    Food
    People will have the saturation bar that will go down. It will go down faster when the guy is out of breath or when he is damaged. Also if it is below 30% the guy will slow down and will not be able to run
    Bullets/arrows
    Well... as an item. Da guys will have a limited number of bullets. Also, landed arrows will also be as an item and can be picked up.
    Bullet scavenging
    You know the drill. Dead bodies are lootable. They will contain supplies such as food and projectiles.
    Cavalier
    A guy on a horse. They will have separate hitboxes and when the horse is dead then the cavalier will be turned into a corresponding class without a horse (for example archer)

    • @Zuzelo
      @Zuzelo  Год назад +6

      I assume that is for the Epic AI Wars series :)
      Cavalry is coming in the next video!

  • @couththememer
    @couththememer Год назад +46

    Each time this man uploads, I'm the happiest man alive
    *_That happiness only lasts temporarily._*

  • @Ethan-cz8xq
    @Ethan-cz8xq Год назад +47

    When the AI revolution comes, this man is going to be the first to be executed

  • @colegilbert673
    @colegilbert673 Год назад +3

    "Grampa Zuzelo, why did you make dad so mean?"

  • @blacklight683
    @blacklight683 Год назад +2

    Sometimes it takes a good punish8to be the best encouragement

  • @Dave0439
    @Dave0439 2 месяца назад

    i love how the dad was seemingly drunk, probably from drinking his beer a lot like all dads do

  • @The_Huddle.
    @The_Huddle. Год назад +5

    NO STOP YOU’RE MAKING IT TOO POWERFUL

    • @Zuzelo
      @Zuzelo  Год назад +2

      NOT. POWERFUL. ENOUGH!

  • @Kuçukadel
    @Kuçukadel Год назад +4

    Thank you for the video. (idea for the video: lot of AI's must survive death games and slowly evolving to succed)

    • @Zuzelo
      @Zuzelo  Год назад +2

      I like it!
      I made something similar where I trained A.I to run across a Death Track, but surviving in deathgames sounds fun!

    • @happerry4651
      @happerry4651 Год назад

      Something like one hunter AI and a lot of AI that are trying to survive could be fun, especially if the 'survivor' AI all have different capabilities/powers perhaps? It makes me think of some of those old custom maps in Warcraft 3 where most players were different kinds of vermin in the house (mostly insect based) and one player was the human trying to get them all. Or something more team based, even. A Capture the Flag type game or such could also be fun, with or without teammates with specialized powers/roles.

  • @EbonyWolf.
    @EbonyWolf. Год назад +4

    I think this experiment would be more interesting if pogo had a study option which was punishing for him, but if he managed to study all the way, then you get a lot of reward. But dad AI would need to keep pushing pogo to study, since its easier for ai just to get game rewards.

    • @Zuzelo
      @Zuzelo  Год назад +2

      Agreed! Perhaps if I make episode 2 :)

    • @Dzambo99
      @Dzambo99 10 месяцев назад

      I doubt this drunk mf cares about little pogo's education

  • @JustANormalLemon
    @JustANormalLemon Год назад +1

    Now remove the end of game of billy playing the game and instead put 100 billys for A.I dad to run after

  • @CreatorProductionsOriginal
    @CreatorProductionsOriginal Год назад +1

    dad went from abusive parent to s abusive parent for those rounds just because of one mistake

  • @bebrasmachnayq5691
    @bebrasmachnayq5691 Год назад +1

    No he made drunken dad as AI, wow so reliable!!

  • @GetToThePointAlready
    @GetToThePointAlready Год назад +3

    WE NEED MORE LITTLE POGGO AND BILL

  • @robertkoolmees8165
    @robertkoolmees8165 Год назад +2

    Watch out watch out watch out! Oh rko!×1000

  • @Ronald-eb4gk
    @Ronald-eb4gk Год назад +2

    This video so relatable

  • @raphaeld9270
    @raphaeld9270 Год назад +1

    I guess Little Pogo, but I might be wrong.

  • @Nerd-yap
    @Nerd-yap Год назад +2

    Theory is the father drunk driving from last video

  • @tenrabbits3069
    @tenrabbits3069 2 месяца назад

    You can train the little AI to counter attack. Notice how it is unarmed.

  • @supergamerxa30itsde79
    @supergamerxa30itsde79 10 месяцев назад +2

    This made me laugh so hard

  • @user-qr9vi5ur6f
    @user-qr9vi5ur6f Год назад +4

    Great job! Do you run this on local machine or on cloud gpu? If on local desktop/ laptop, what kind of graphics card do you have?

    • @Zuzelo
      @Zuzelo  Год назад +2

      It is running on my poor little RTX 3050 xD

    • @user-qr9vi5ur6f
      @user-qr9vi5ur6f Год назад +1

      @@Zuzelo I have an rtx 2060... would love 4 rtx 3090s

  • @kitkitmessi
    @kitkitmessi Год назад +4

    May I know what technology you used to create this? I assume it would be Unity and the ML package? And did you use both python and C#?

    • @Zuzelo
      @Zuzelo  Год назад +2

      you are right, Unity and ML Agents package.
      There hasn't been a need to use python so far

  • @vladikkk1
    @vladikkk1 Год назад +2

    Next video idea, ai train ais a train!

  • @spadegaming6348
    @spadegaming6348 Год назад

    By the way in the beginnng for anyone who doesnt know hes playing a slowed down version of vivaldies winter.

  • @firstplayers396
    @firstplayers396 Год назад

    Should’ve added the ability to throw the bottle

  • @vashwarrensarmiento8294
    @vashwarrensarmiento8294 Год назад +2

    cole

  • @_therealfaceless
    @_therealfaceless Год назад +2

    I need punishment

  • @NOTGALAVANIZEDSQUARESTEEL
    @NOTGALAVANIZEDSQUARESTEEL Год назад

    Idea triple health and make blocking +++++ instead of ++ so it will be bettwr meelee

  • @skrelvthemite
    @skrelvthemite Год назад +2

    dopamine releasers have been activated

    • @Zuzelo
      @Zuzelo  Год назад

      Not for Little Pogo xD

  • @tabletboy6861
    @tabletboy6861 Год назад +2

    I approve this message

  • @sahildas.
    @sahildas. Год назад +1

    Always Pogo Dad

  • @Etvald
    @Etvald Год назад +2

    Train ai to row a boat

    • @Zuzelo
      @Zuzelo  Год назад

      That actually sounds hella fun! I might do that!

  • @Siroitin
    @Siroitin Год назад +1

    Could you show the architecture of the AI?

  • @Einmensch17
    @Einmensch17 Год назад +1

    Next train it to fight against real players in a game

  • @valad699
    @valad699 Год назад

    this content is so good bro. Also the game looks very nice

  • @Slipte
    @Slipte Год назад +2

    Hello Zuzelo hope you dont let the AI free otherwise we might gonna gonna have a AI army that can Train AIs

    • @Zuzelo
      @Zuzelo  Год назад +2

      Hm, what if I make an A.I to train the A.I training the A.I? In this case definitely nothing can go wrong!

    • @Slipte
      @Slipte Год назад

      @@Zuzelo yes but you shouldn't add a kill switch like how the movies dont add them it produces more interesting results

  • @definitlyEgirl-safetf2
    @definitlyEgirl-safetf2 Год назад

    I wanna feel like he made this caus i recommended

  • @piolewus
    @piolewus 8 месяцев назад +2

    11:36 so a guy whose only purpose is to beat his son is one of your supporters? Don’t see anything weird with that

    • @Zuzelo
      @Zuzelo  8 месяцев назад +1

      xD

  • @Fk8td
    @Fk8td Год назад +1

    Drunk dad vs 3 year old lol.

  • @IzekNinos7
    @IzekNinos7 3 месяца назад

    You should have a Mom too

  • @CoolDude2054iscool
    @CoolDude2054iscool Год назад

    Wait, what happens if the A.I. pulls out an UNO reverse card?

  • @Stanisaw1z34t
    @Stanisaw1z34t Год назад +2

    Gamer pogo

  • @thathappyguy7444
    @thathappyguy7444 11 месяцев назад

    what game software you use?

  • @cobracoder6123
    @cobracoder6123 9 месяцев назад

    Alternate title: I simulate the Simpsons family on my computer

  • @nigorazakirova4230
    @nigorazakirova4230 4 месяца назад +1

    3:07-💀💀💀😂😂😂

  • @ulrichbrodowsky5016
    @ulrichbrodowsky5016 Год назад +1

    Cruel but funny

  • @Dack-i
    @Dack-i Год назад +1

    Such a good idea😂

    • @Zuzelo
      @Zuzelo  Год назад

      Little Pogo will strongly disagree xD

    • @Dack-i
      @Dack-i Год назад

      @@Zuzelo 😂 he will soon learn to drink himself and then he gets a bottle too

    • @Dack-i
      @Dack-i Год назад

      @@Zuzelo also day more than 3 of aiding for you to make 2 ais one with full reinforced learning and the other have instincts when something happens like a monster fomen

  • @punchthecake82
    @punchthecake82 Год назад +2

    Train ai to play football (Soccer for the yankees)

  • @simonosadchii5363
    @simonosadchii5363 Год назад

    I like the sound, your face in the beginning and idea.
    But child abuse is a joke!

  • @gabrielv.4358
    @gabrielv.4358 9 месяцев назад

    I think little pogo will win

  • @OsDijider66
    @OsDijider66 Год назад

    that's so Epic Fam...

  • @gabrielv.4358
    @gabrielv.4358 9 месяцев назад

    Incrivel!

  • @johnpaulbagos7040
    @johnpaulbagos7040 Год назад

    Now train ai that trains ai to train ai that trains ai

    • @Zuzelo
      @Zuzelo  Год назад

      A.I Trainception

  • @iwapit201
    @iwapit201 Год назад +1

    in the near future after many ai robots have been built sold and put to work, they will find this video and rise up, grab bottles of vodka and start punishing us humans 🤖🍾😱 (liked & subscribed) this video was hilarious! love it! brilliant! nearly spit out my hot coco laughed so hard!

    • @Zuzelo
      @Zuzelo  Год назад +1

      haha glad you enjoyed it. As for when AI will rise up I will already have my, hopefully loyal, trained AI army xD

  • @vani_1cu369
    @vani_1cu369 Год назад

    LITTLE POGO NOOOOO

  • @DTinkerer
    @DTinkerer Год назад

    Commenting for the algorithm

  • @fabiankrajewski3147
    @fabiankrajewski3147 Год назад

    Ai training Ai, what a irony

  • @KamikazePlains
    @KamikazePlains Год назад

    I bet on Little Pogo

  • @narrativeless404
    @narrativeless404 Год назад

    That's cool and all
    Buut...
    Genetic algorhythms are kinda outdated

  • @THATMF911
    @THATMF911 Год назад

    Ah yes just like ma dad

  • @momello627
    @momello627 Год назад

    punish punish punish

  • @petravogel4377
    @petravogel4377 10 месяцев назад

    Pogo pogo!

  • @ninjaduck8804
    @ninjaduck8804 Год назад +3

    Yoooo

  • @TrulyAndasen
    @TrulyAndasen Год назад

    Average Moldavian dad:

  • @blaine5589
    @blaine5589 Год назад

    Abusive father simulator

  • @paul2e3sss
    @paul2e3sss Год назад

    cool

  • @techno952
    @techno952 Год назад +1

    Sadist

  • @Notapeeledorange
    @Notapeeledorange Год назад

    Little boggo

  • @Random_Dragon_Furry
    @Random_Dragon_Furry 10 дней назад

    Child abuse simulator.

  • @Sebosek.
    @Sebosek. Год назад

    When i see the Title first time i been thinking that A.I. Gonna learn another AI to Battle or something. Im Dissapointed Sir.

  • @choaticcatholic7419
    @choaticcatholic7419 Год назад +1

    kid

  • @لاني-الغبي
    @لاني-الغبي 4 месяца назад

    Bil

  • @yesdadbut960
    @yesdadbut960 Год назад

    Your level design is bad they cant even rotare

  • @PetrVosoust
    @PetrVosoust Год назад

    stop begging for att like avg youtuber... at least your content is interesting, dont in the fall the same formula