Can AI Destroy Mario Kart Wii's Time Trials?

Поделиться
HTML-код
  • Опубликовано: 11 ноя 2024

Комментарии • 242

  • @NMeade
    @NMeade Месяц назад +305

    This video was AWESOME, so cool to see the entire process for approaching this. Would be really cool to see this for other tracks!

    • @aitango
      @aitango  Месяц назад +39

      Hey NMeade, I’m a huge fan of your channel! Would love to work with you if ever you’re looking for a new video idea, including trying some other tracks

    • @haiden9170
      @haiden9170 Месяц назад +6

      @@aitango maybe on Maple Treeway , it's is her favorite track ( if i remember correctly ) or Mario Raceway i don't remember

    • @aitango
      @aitango  Месяц назад +14

      I’m good for either of those if he wants to :)

    • @Scalene17
      @Scalene17 Месяц назад +11

      NMeade versus the ai on his big bad castle

    • @kazii_the_avali
      @kazii_the_avali Месяц назад +1

      @@aitango ngl i would love to see maby some fanmade tracks

  • @Random_Guy-rm4tv
    @Random_Guy-rm4tv Месяц назад +581

    WERE GETTING REPLACED WITH THIS ONE 🔥

    • @aitango
      @aitango  Месяц назад +61

      No one will stop people playing Mario Kart AI haha

    • @Random_Guy-rm4tv
      @Random_Guy-rm4tv Месяц назад +31

      @@aitango honestly it would be a cool idea if theres some CPU levels that are just a well trained ai,this would be very helpful in some games like smash bros since the cpu 9 is just broken (and broken as weird and not insanily good because it have some weird outputs)

    • @rembartx
      @rembartx Месяц назад

      @@aitangoare you gonna make a rocket league ai😢

    • @CrossyChainsaw
      @CrossyChainsaw Месяц назад

      @@Random_Guy-rm4tvon it

    • @thuyenlee8995
      @thuyenlee8995 Месяц назад +3

      * Wii are

  • @NathanWoyessa
    @NathanWoyessa Месяц назад +189

    This is who I thought TAS was as a kid

    • @alansmithee419
      @alansmithee419 Месяц назад +24

      In a way this is a TAS.
      It's very different from other TASes but still.

    • @alphamaxabel1397
      @alphamaxabel1397 Месяц назад +1

      Same 😭🙏

    • @nvna1111
      @nvna1111 12 дней назад

      Same lol

  • @masqmp3
    @masqmp3 Месяц назад +202

    really enjoyed editing this one!

    • @aitango
      @aitango  Месяц назад +52

      Really glad you enjoyed it, amazing job with the editing, couldn’t be more happy

    • @Kat21
      @Kat21 Месяц назад +2

      whats the song at 0:37 i think ive heard it before

    • @masqmp3
      @masqmp3 Месяц назад +1

      ​@@Kat21 The swimming mini game on Wii Party 👍

    • @xiaolin867
      @xiaolin867 Месяц назад +3

      So you're the one that added the unnecessary, attention-span subtitles...

    • @winterispretty6464
      @winterispretty6464 Месяц назад

      bro plays osu what a true gamer

  • @campbellblock3061
    @campbellblock3061 Месяц назад +144

    It’s so cool to see how far the AI project has come. It’s even starting to use preliminary quickhops! But one thing that would save an enormous amount of time is timing the chain wheelies. I noticed that the wheelie input is just being spammed every other frame on straights and that seems to result in half chains every time. Timing the chain 181 frames after the first wheelie would improve this considerably on LC, and it would also help to not fill up the input file on longer tracks later down the line.

    • @craftyawesome6830
      @craftyawesome6830 Месяц назад +10

      He mentions at 7:49 that it only inputs every 2 frame, so it is possibly not wheelieing for multiple frames per chain. (in fact missing 3 frames every time if I understand correctly)

    • @clouds-rb9xt
      @clouds-rb9xt Месяц назад +1

      @@craftyawesome6830Why not every frame then

    • @craftyawesome6830
      @craftyawesome6830 Месяц назад +5

      @@clouds-rb9xt Probably performance. 30hz inputs instead of 60 means half the amount of times you need to compute the inputs the AI chooses.

    • @clouds-rb9xt
      @clouds-rb9xt Месяц назад

      @@craftyawesome6830 Need a super pc tbh

    • @lorenzosotroppofigo1641
      @lorenzosotroppofigo1641 Месяц назад

      ​@@clouds-rb9xtHe already has a beast pc. Neural networks are expensive

  • @Loki_SR
    @Loki_SR Месяц назад +49

    Been waiting for an installment like this into this little series since the beginning. Commenting to let you know I would LOVE to see more

    • @aitango
      @aitango  Месяц назад +18

      I’m pretty confident this won’t be my last time trial attempt :)

    • @aitango
      @aitango  Месяц назад +9

      I’m pretty confident this won’t be my last time trial attempt :)

  • @LuckyHamburger
    @LuckyHamburger Месяц назад +32

    Personally I would have opted to get the ai to take tighter lines by making the checkpoint reward proportionally to how close it gets to the wall. I'm not sure how feasible or useful that would actually be but I'd love to hear your thoughts.

    • @FuzzyJeffTheory
      @FuzzyJeffTheory Месяц назад +26

      You have to be careful introducing extra rewards, as it can lead to suboptimal behavior. The AI might slow down a lot to get as close to the wall as possible

    • @fishymario
      @fishymario Месяц назад +6

      @@FuzzyJeffTheory is right.

  • @UrMumLuvsUHun
    @UrMumLuvsUHun Месяц назад +10

    Your way of getting the AI to do shortcuts is really smart, it never clicked with me that it wouldn't just do that on its own

    • @aitango
      @aitango  Месяц назад +5

      Yeah that's pretty much expectation vs reality in AI... if it can take an easier route, it almost always will

  • @fluffsquirrel
    @fluffsquirrel Месяц назад +1

    I've been so excited waiting for this! Fantastic execution and thank you for explaining your methodology!

    • @aitango
      @aitango  Месяц назад +1

      You're very welcome, really glad you enjoyed it! I'm far from finished with time trials too

    • @fluffsquirrel
      @fluffsquirrel Месяц назад

      @@aitango Epic! I'm so glad, looking forward to it! Amazing work as always

  • @mango10152
    @mango10152 Месяц назад +7

    another banger! good job

    • @aitango
      @aitango  Месяц назад +1

      Appreciate it!

  • @dhplaz1475
    @dhplaz1475 Месяц назад +5

    The AI ​​on the last lap drove towards the finish line with an uneven angle. It would have reached its destination faster if it went straight ahead.

  • @8_chips296
    @8_chips296 Месяц назад +26

    ai: insanely good at the game
    logan: still somehow better

    • @aitango
      @aitango  Месяц назад +17

      Logan is too powerful, but the gap is closing…

    • @greengreenanimations
      @greengreenanimations 7 дней назад

      Robots are controlled by humans

  • @Known_as_The_Ghost
    @Known_as_The_Ghost Месяц назад +1

    These videos are so enjoyable to watch.
    Thank you c:

    • @aitango
      @aitango  Месяц назад +1

      Glad you like them!

  • @itim4329
    @itim4329 7 дней назад

    Amazing, what is possible these days! Keep up the great and innovative work man.

  • @Renardeau
    @Renardeau Месяц назад +10

    still , now it seem possible to go beat the wr

    • @aitango
      @aitango  Месяц назад +13

      Feels so close… one day

  • @BenziDK
    @BenziDK Месяц назад +1

    your videos are much work, thx for that tho!

    • @aitango
      @aitango  26 дней назад

      Glad you like them!

  • @AndyLundeen
    @AndyLundeen Месяц назад +1

    I'm looking forward to watching the AI mogi and clan wars after they get TTs conquered. Incredible work!

    • @aitango
      @aitango  Месяц назад

      AI vs Human clan wars would be so much fun, even way harder than time trials

  • @rodafy9110
    @rodafy9110 Месяц назад +1

    was looking forward to seeing it develop this far. it's good enough to beat me on LC now... would be cool to see the AI eventually learn how to play online!

  • @Goomey
    @Goomey Месяц назад +2

    This is extremely impressive wow, there is very little left to optimize at this point.
    The only immediate things I could think of would be a delayed drift (that way you don't have to hop to align for the back straight) and then obviously chain wheelies

    • @aitango
      @aitango  Месяц назад

      Technically kind of I guess

    • @Goomey
      @Goomey Месяц назад

      @@aitango I'm just nitpicking at this point, the vid is insanely well made and easy to follow, please make more! :D

  • @TomMKW
    @TomMKW Месяц назад +2

    haha the ai actually learned how to do TAS hops. that is so cool.

    • @aitango
      @aitango  Месяц назад

      Yeah it was really cool that it actually figured that out by itself

  • @aname4390
    @aname4390 Месяц назад +1

    Based video. Grumble Volcano no ultra sounds like a challenge.

  • @ace_beaton
    @ace_beaton Месяц назад +2

    Solid video mate.

    • @aitango
      @aitango  Месяц назад

      Much appreciated!

  • @ImJustCath
    @ImJustCath Месяц назад +4

    That slick subscribe insert made me laugh and got me to, GG.~

    • @aitango
      @aitango  Месяц назад +1

      Did it work? :)

    • @ImJustCath
      @ImJustCath Месяц назад

      @@aitango That's what I meant by "Got me" I'm in. UwO

  • @jaimegarcia4442
    @jaimegarcia4442 6 дней назад +1

    As a data scientist dealing with NLP mainly, it would be amazing to see the code behind this. Is there any chance we get to see some code snippets? Congratulations for the great job!

  • @KlaroNebulous
    @KlaroNebulous Месяц назад +1

    Keep this stuff going🙏

    • @aitango
      @aitango  Месяц назад

      Will do for sure!

  • @atomicstorm7006
    @atomicstorm7006 Месяц назад +6

    Is there any way you could train ai by letting it analyze other people’s inputs? For example you could let it watch the top 100 times on a course over and over and let it train that way.

    • @lorenzosotroppofigo1641
      @lorenzosotroppofigo1641 Месяц назад +2

      Doesn't make any sense to train an AI on the same dataset "over and over again".
      Also it's a completely different model and the dataset is too small. What you are asking is so infeasible that the first time this was done with good results was like 6 months ago by OpenAI.
      I mean they tried before, but it wasn't that good

    • @llaw176
      @llaw176 24 дня назад

      @@lorenzosotroppofigo1641imitation learning using the wr ghost seems feasible to me?

    • @lorenzosotroppofigo1641
      @lorenzosotroppofigo1641 24 дня назад

      @@llaw176 Yeah but if you are using only one ghost it's overfitting tho, not learning
      100 aren't enough either

  • @athehybrid
    @athehybrid Месяц назад

    awesome video as always!

    • @aitango
      @aitango  Месяц назад +1

      Really grateful for the support!

  • @TheGamerMan64
    @TheGamerMan64 Месяц назад +2

    This is all really cool, any chance you could help a brother out and show me resources to learn how to do this myself? Or perhaps a video tutorial on a smaller scale?

  • @117james
    @117james Месяц назад

    LETS GOOOOOOOOOOOOOOO IVE BEEN WAITING FOR THIS

    • @aitango
      @aitango  Месяц назад

      Good to hear you were excited!

  • @lucascowdenisawesome
    @lucascowdenisawesome Месяц назад +1

    Amazing video your RL models are really great to see in action. Do u by any chance ever share your repos or have a vid walking through the basics of your code? I’m trying to learn RL more and would be great to learn through exploring it in a context/game I love

    • @aitango
      @aitango  Месяц назад +1

      I currently haven't made the repo public, however will do once I reach 100k subs. I'm currently trying to publish the algorithm I used for this video, and if it gets published I'll for sure do a video on it

  • @SSLuis98
    @SSLuis98 Месяц назад +1

    This is quite impressive, huge advancements were done. I suppose you could create agents for each track so the AI would depend on them whenever it plays, this would he useful when playing against other players / cpus?

  • @chaoscodytv
    @chaoscodytv Месяц назад +1

    Yay a new post!

  • @manfredi19
    @manfredi19 Месяц назад

    such a good video, keep it up

    • @aitango
      @aitango  Месяц назад

      Thanks, will do!

  • @binkabla
    @binkabla 4 дня назад

    This is not AI, youre making this ghost with human intelligence

  • @BOIgaming33
    @BOIgaming33 17 дней назад

    We’ve seen multiple wii games on this channel (don’t get me wrong, wii games were goated), but I wonder if you could make an AI for other consoles (Ex: Gamecube, N64, 3ds). Personally, I’d love to see a Mario Kart Double Dash video someday.

  • @サビン-w5j
    @サビン-w5j Месяц назад +2

    Do you think it will be possible to teach an AI a tech track like CM or bowsers castle?

    • @aitango
      @aitango  Месяц назад

      Definitely possible, the main problem would be my knowledge setting it up!

  • @_Dxnny
    @_Dxnny Месяц назад +1

    I have no idea how any of this works but could you get the AI to watch how the WR plays the track to copy and improve on it?

  • @elvsrbad2
    @elvsrbad2 Месяц назад

    I would have liked to see if it could have found that shortcut on its own without the out of bounds area, but overall good job!

  • @kiunthmo
    @kiunthmo Месяц назад

    you could pretrain on ghost data. would be interesting to know more about how you were able to actually get the data, whether there were tricks to make it run faster, etc

  • @Khari99
    @Khari99 Месяц назад

    I believe it should be mathematically possible to calculate the minimum time between checkpoints. Then you can reward it more the closer it reaches this ideal

  • @alganpokemon905
    @alganpokemon905 Месяц назад +2

    great vid. the ultimate would be an agent that can play unseen tracks lol. how much compute would that take?

    • @aitango
      @aitango  Месяц назад

      Glad you liked it. Would probably take ages, especially if I individually design the rewards for each track.

    • @alansmithee419
      @alansmithee419 Месяц назад +1

      He has tested things like unseen tracks before, but they've never been very good at them.
      He did however find that the AI could adapt to new tracks very quickly via further training if it had prior training on a few others.

  • @sumanthmoole
    @sumanthmoole Месяц назад

    this is so cool i want to see more

    • @aitango
      @aitango  Месяц назад

      I’ll be sure to keep it coming!

  • @sephikirb
    @sephikirb 8 дней назад

    What if all the checkpoints were the one checking your lap progress, would the ai find some new lap skipping method on some maps ?

  • @DDoig1
    @DDoig1 Месяц назад

    The vocal fry is crazy :D

  • @BillboMC
    @BillboMC Месяц назад +1

    I’m surprised it didn’t master chain wheelies? Or is that a side effect of it not being able to input every frame?

    • @aitango
      @aitango  Месяц назад +1

      That part was my fault, due to the way the wheelie action was programmed. Will certainly be fixed in the next video!

  • @29lovvan
    @29lovvan Месяц назад

    Never heard more vocal fry in a commentary before

  • @GreenAndYellowOfficial
    @GreenAndYellowOfficial Месяц назад +1

    hey when can you test the ai in mario kart 7?

    • @aitango
      @aitango  Месяц назад

      When I can get an emulator to work for MK7, although sadly it doesn't look too likely

    • @BOIgaming33
      @BOIgaming33 17 дней назад

      @@aitangoi mean there’s citra. it may have been taken down awhile back, but it’s still downloadable.

  • @preacherm4n
    @preacherm4n Месяц назад

    good video! now have the ai learn how to superhop lol

    • @aitango
      @aitango  Месяц назад

      Thanks!! That would take quite a bit of training haha, although still possible I think

  • @epicawesomesauceguy
    @epicawesomesauceguy Месяц назад +1

    i love this. have you tried using continuous actions for the steering instead of 5 discrete ones? it may not be necessary but i'm curious

    • @aitango
      @aitango  Месяц назад

      The method I’m using doesn’t actually allow continuous actions, however is far more sample efficient than those methods. I’m not sure how big an improvement adding more angles would actually give it, after like 7 you’d probably get diminishing returns

  • @14sirs
    @14sirs Месяц назад +2

    W masq moment

  • @ObeisantBug3808
    @ObeisantBug3808 Месяц назад +1

    do you have the ghost for this still?
    I would like to race it because it beats me by .1 and that end time is about my short term goal on the track

    • @aitango
      @aitango  Месяц назад +1

      If I remember I might post it on my discord server sometime soon

  • @CodeChrisB
    @CodeChrisB Месяц назад

    Hey any way to get some information on what tools you used . I certainly have the skills to do so I have a degree in theoretial AI design but never touched AI gaming.
    Even better would be perhabs soms source code? I know thats quite a lot to ask for but any help would be appreciated. Im a retired software developer (23 yrs old lmao) and think creating an AI of my favourite mario kart would just be amazing

  • @mkwpatsfan
    @mkwpatsfan Месяц назад +1

    How did the AI learn how to quick-hop?

    • @aitango
      @aitango  Месяц назад

      It taught itself through trial and error, I just gave it the controller.

  • @Hélène-b9t
    @Hélène-b9t Месяц назад +2

    I never seen such a great video!

    • @aitango
      @aitango  Месяц назад

      Wow, thanks for the support!

  • @spacebarium
    @spacebarium Месяц назад +1

    goddamn how did it learn to do TAS hops

    • @aitango
      @aitango  Месяц назад

      Honestly no idea how it figured out how to do the optimised shortcut, really blew me away

  • @nobafan7515
    @nobafan7515 Месяц назад +1

    This is amazing. Do you know where i can learn how to program an ai like you did? Is there a youtube tutorial that sets this up? So far i seem to find out of date tutorials or none that tun while the agent is shown playing as the ai trains. Any help would be really appreciated.

    • @aitango
      @aitango  Месяц назад +2

      Really glad you like it! There aren’t any tutorials yet for setting up Mario kart, but lots of reinforcement learning courses. I particularly like deep lizards courses on RUclips, and the book reinforcement learning by Sutton and Barto. Learning to use the python library gymnasium will give you an idea on how to set this up

    • @nobafan7515
      @nobafan7515 Месяц назад

      @@aitango thanks. I'll look into those.

  • @Ifx-
    @Ifx- Месяц назад

    is it possible to make an ai that can play any track its given, even if its never seen it before? so that instead of getting really good at one track its getting good at the game as a whole and applies that skill to any new track?

  • @6700adam
    @6700adam Месяц назад

    Find this so cool people like you exist

  • @relt1554
    @relt1554 Месяц назад

    Is it faster to hop to cancel a wheelie or just cancel the wheelie via the "tilt Wii-remote back down" input?

    • @khirek5335
      @khirek5335 Месяц назад +1

      They're equal but hops are more reliable and you only really stop a wheelie when you want to take a turn and start drifting anyway

  • @flambambam
    @flambambam Месяц назад

    Now I'm curious what this ai could get with shooting star. I hold the outside drift bike bkt of 1:12.108, which I think is pretty dang good for the combo.

  • @TheVoiceofTheProphetElizer
    @TheVoiceofTheProphetElizer День назад

    I'm curious to see what this was coded in.
    EDIT FROM 11/10/2024 - 3:54 PM CST:
    Looks like Python from the code snippets.

  • @breezyx976
    @breezyx976 Месяц назад +10

    What would happen if you made an AI to calculate the expected remaining time to complete the lap, based on the current state, so the main AI knows what to optimize? (I forget what this is called). Or is that what you do already?

    • @alansmithee419
      @alansmithee419 Месяц назад +2

      This sounds like a form of proximal policy optimisation (PPO).
      Have a second AI that estimates the time it will take the driver to complete the race if it performs a certain input at the current time, and then learns how good its guess was based on the actual time it takes, so it then adjusts the best input the driver should have taken, and the driver constantly adjusts to be more likely to use the move that the second AI predicts is best.
      Is this what you meant?
      He is using a form of PPO, but I believe he's using it on the reward function, rather than on "time to complete the race", as that often results in an extremely difficult learning process for the AI. This is why reward functions are used in cases like this.

    • @aitango
      @aitango  Месяц назад

      All reinforcement learning algorithms learn some type of reward, however this can be based on time remaining. The algorithm I’m using is an advanced version of Rainbow DQN. This is a value-based RL method, unlike PPO which is called a policy gradient method.

  • @GarkadeXD
    @GarkadeXD Месяц назад

    Let’s see your ai do n64 sherbet land glitch lol

  • @gloriousglider8-yt
    @gloriousglider8-yt 15 дней назад +1

    Open source? It would help everyone! Great bot, by the way!

    • @aitango
      @aitango  15 дней назад +1

      I said I’d make it open source at 100k subs, however when I made that promise I thought it would happen sooner haha

    • @gloriousglider8-yt
      @gloriousglider8-yt 15 дней назад +1

      @@aitango Do you mind just saying what libraries you use, please?

  • @14sirs
    @14sirs Месяц назад +1

    What are the specs on the PC that you are training your AI on?

    • @aitango
      @aitango  Месяц назад +2

      Check out my video evolution of my Mario kart ai. In that one I go over how it all works, including the hardware I run it on

  • @KINGitaly
    @KINGitaly 7 дней назад +1

    Make It play ai minecraft

  • @mkwpatsfan
    @mkwpatsfan Месяц назад

    Can you make the A.I time trial DK Summit next?

    • @aitango
      @aitango  Месяц назад

      I’m not sure which track to do yet! Trying to get the AI to do the double cut would be fun haha

  • @namesurname4666
    @namesurname4666 Месяц назад +1

    I hope wiimmfi won't have AI

    • @WestinSmiqth
      @WestinSmiqth 24 дня назад +1

      i think this wont be very probable/plausible, connecting an ai up to say an emulated controller for online play will be much harder and slower than giving direct inputs locally, so unless theres a different way most ai's would play horribly on wiimmfi due to local lag, also the non-local lag in general will also screw it up, also also the ai would probably need to learn how to aim/time items, which will be very difficult to do, so yeah, very unlikely

  • @samuelzackrisson8865
    @samuelzackrisson8865 Месяц назад

    Really interesting video. I have a quick question though how do you play multiple ghosts at the same time in tas tools?

    • @aitango
      @aitango  Месяц назад

      There’s a program on dolphin called sp-mkwii.

  • @117james
    @117james Месяц назад

    Great! Now teach it ultra shortcuts :D

  • @antiantiderivative
    @antiantiderivative Месяц назад +1

    Python moment 🤩

  • @Esto12
    @Esto12 Месяц назад

    What did you use to be able to get the values from dolphin ram into python?

    • @aitango
      @aitango  Месяц назад +1

      I’m using a fork of dolphin which allows me to interact with the emulator in python. Check out my video evolution of my Mario Kart AI to see more

  • @samuraimaster321
    @samuraimaster321 Месяц назад +1

    A sense of proudness lol

    • @aitango
      @aitango  Месяц назад

      It’s quite weird but it’s definitely there

  • @lonelyPorterCH
    @lonelyPorterCH Месяц назад

    Dang thats impressive :D

    • @aitango
      @aitango  Месяц назад

      Thanks! Still want to get that wr though

  • @RazorBird
    @RazorBird Месяц назад

    Thanks!

  • @tascreeper
    @tascreeper Месяц назад

    that is insane.

    • @aitango
      @aitango  Месяц назад +1

      Yeah pretty crazy, I hope one day I’ll get the world record

  • @ruhenot6682
    @ruhenot6682 Месяц назад

    Very interesting video.
    I'd suggest to cut down on the subtitles though and only use it if you want to emphazise what youre saying. You have a very soft spoken and clear voice. Constantly having text on screen is stressful and in your case just unnecessary.. :)

    • @aitango
      @aitango  Месяц назад +1

      Glad you liked it! Yeah might try using them slightly less and see how the videos do

  • @bytebeamer
    @bytebeamer Месяц назад

    Can you make an ai to play taiko no tatsujin?

  • @Saxofome
    @Saxofome Месяц назад +2

    AI or TAS.They're not similar to each other

    • @aitango
      @aitango  Месяц назад +2

      I think world records will soon need a new category

    • @WestinSmiqth
      @WestinSmiqth 24 дня назад

      kind of like how chess has a computer championship maybe one day an MKWii speedrun category will exist, i would call it "MKAii"

  • @CrossyChainsaw
    @CrossyChainsaw Месяц назад

    Read memory from the ram? How?

    • @aitango
      @aitango  Месяц назад

      There’s a program called dolphin memory engine, it’s very useful

  • @scruffypantz12
    @scruffypantz12 Месяц назад

    name the AI Funky AI

    • @aitango
      @aitango  Месяц назад

      Any suggestions?

    • @scruffypantz12
      @scruffypantz12 Месяц назад

      @@aitango you try to beat the AI on rainbow road!!

  • @ДаниярКадамбаевич
    @ДаниярКадамбаевич Месяц назад

    Мне кажется Или это искусственный интеллект скоро появится сингулярность где он бесконечно усовершенствовать себя в игре Mario Kart это будет безумие а потом он захватит весь мир я смотрю твоё первое видео и вначале он был таким то что ошибался в начале трассы😂😂😂😂

    • @ДаниярКадамбаевич
      @ДаниярКадамбаевич Месяц назад

      Те кто не знает что такое сингулярность Это такая вещь то что у искусственного интеллекта есть сингулярность а это значит он будет обучаться до бесконечности то есть усовершенствовать себя Он играет в одну игру как например Mario Kart а потом он переходит на другую игру потом создаёт своё ии потом заканчиваются все игры переходят на приложение потом на телефон потом на роботов а потом захват мира их невозможно задержать даже если вы запихнули самую защищённую во Вселенной компьютером рано или поздно он просто Придумай как выбраться из компьютера

    • @WestinSmiqth
      @WestinSmiqth 24 дня назад

      maybe google translate goofed up what you said, but that was not coherent at all, what?

  • @pisiu2484
    @pisiu2484 Месяц назад +1

    What's the name of the song from 8:05?

  • @andy02q
    @andy02q Месяц назад

    TAS is 1:02:446. If it can't beat that using TAS tools, then not much point to it.

  • @noahcheng1895
    @noahcheng1895 Месяц назад

    can it play bowser's castle?

    • @aitango
      @aitango  Месяц назад

      It can play any track in theory, I just need to help designing the reward function!

  • @Stabidistabstab_PBP
    @Stabidistabstab_PBP Месяц назад

    Are you going to put in more rewards and penaltys or is this it?

    • @aitango
      @aitango  Месяц назад +2

      Since posting I have a few more ideas to improve things, but that’s for next video haha

    • @Stabidistabstab_PBP
      @Stabidistabstab_PBP Месяц назад

      so there is a chance, pog

  • @Kragnar1
    @Kragnar1 7 дней назад

    666? I’m scared.

  • @Revi-j7m
    @Revi-j7m Месяц назад

    Video starts at 8:10

  • @EnkiCarrillo-nl8sm
    @EnkiCarrillo-nl8sm 5 дней назад

    I think I am on 1:17

  • @WizardOnYoutube
    @WizardOnYoutube Месяц назад

    We need to take the ai and the game and subtract the rendering so it can play many many many instances a second
    Run the game such that it does like 10-15 races a second and let it run for a year😊

    • @aitango
      @aitango  Месяц назад

      There’s a cool project doing something similar called kinoko which is looking to reverse engineer the physics engine. My ai uses images as input though, so sadly I still need to render the image

  • @Dalibre1
    @Dalibre1 8 дней назад

    make an ai that can superhop or do ultras

  • @icefire4814
    @icefire4814 7 дней назад

    Nice one

  • @jjcookierock
    @jjcookierock Месяц назад

    ChatGPT Kart Wii

  • @LLInnovA
    @LLInnovA Месяц назад

    tfw your pr is slower than an AI generated run :(
    I want to see it try all the tracks. You should also provide the ghost so we can race against the AI

    • @aitango
      @aitango  Месяц назад

      It’s in my discord server if you want to try

  • @Grofvolkoren
    @Grofvolkoren Месяц назад +1

    Awesome videos, but you have a lot of vocal fry in your voice. Are you aware of that?
    Still a fan of what you are doing.

    • @aitango
      @aitango  Месяц назад +1

      Sorry about that, I didn’t notice anything myself. Glad you could still enjoy it though. I’ll try and sort it out

    • @masqmp3
      @masqmp3 Месяц назад

      hi, we used adobe's podcast ai to enhance the microphone audio. the original audio doesn't have the 'vocal fry', instead it's the podcast ai emulating a high quality studio microphone 👍

  • @carolinefell4505
    @carolinefell4505 Месяц назад +1

    Under 30 minutes gang

    • @aitango
      @aitango  Месяц назад

      Dedicated fan, much appreciated

  • @Alo-nq1ot
    @Alo-nq1ot Месяц назад

    Ai does puyo puyo pls. The ones in game are not by neural network learning.

  • @GuyThatCREATESRandomStuff
    @GuyThatCREATESRandomStuff 4 дня назад

    9:09 word mixing.

  • @shockds13
    @shockds13 Месяц назад

    Am I the only one who feels bad for the AI?

  • @gabrielechioda7069
    @gabrielechioda7069 Месяц назад

    Impressive