AI Learns to play Geometry Dash || Part 2

Поделиться
HTML-код
  • Опубликовано: 16 ноя 2024
  • НаукаНаука

Комментарии • 490

  • @CodeNoodles
    @CodeNoodles  2 года назад +59

    Hey, I decided to make a part 3 to play some more levels as you guys requested! ruclips.net/video/A3JJsjZLRSo/видео.html

    • @JavaCake
      @JavaCake 2 года назад

      :)

    • @laty9f1
      @laty9f1 2 года назад +1

      Hey man I love your video but please make the screen behind your png thing dark instead of white. I got my retinas burned out at 2 am😅

  • @TrideGD
    @TrideGD 2 года назад +1075

    This AI is WAY too human-like, it struggled with the triple spike. The AI takeover is upon us

    • @DeMooniC
      @DeMooniC 2 года назад +37

      Yo what's up tride lol
      And yeah I didn't expect it at all to get so far just in the third attempt and struggle with the triple like a real human would do xd. Pretty insane stuff

    • @UnknownedYt
      @UnknownedYt 2 года назад +3

      Tride

    • @pul-sor
      @pul-sor 2 года назад +6

      i didnt excpect tride to be here lol

    • @HEJOK254
      @HEJOK254 2 года назад +16

      It even learned straight fly

    • @dirhi
      @dirhi 2 года назад +5

      hi hello hi

  • @BusterBrown1217
    @BusterBrown1217 2 года назад +719

    The network literally found the MOST anxiety inducing way to fly through that part.
    I'm not sure if I like it or not.

    • @mazenyasser7208
      @mazenyasser7208 2 года назад +68

      Because it only clicks when it's absolutely necessary, not like us who may click for the fun of it.

    • @killcrap1
      @killcrap1 2 года назад +12

      I was stressed watching the first time it got to 63 percent, it had so many near misses

    • @tungleson7066
      @tungleson7066 Год назад

      ​@@mazenyasser7208Not a player but aren't that the best way of playing?

    • @circumplex9552
      @circumplex9552 Год назад

      ​@@tungleson7066no, its much more risky to do minimum clicks in ship sections

  • @abugidaiguess
    @abugidaiguess 2 года назад +1285

    the AI struggling at 63% for generations is pretty relatable tbh

  • @AceTechn0
    @AceTechn0 2 года назад +607

    Dang Generation 3 carried hard, that last cube seriously changed the Best Attempt from like 12% to 63% solo

  • @Commander_Chopper
    @Commander_Chopper 2 года назад +245

    It would be very interesting to see how the winner network would perform on a completely different level.

    • @firefoxgamingpg3d
      @firefoxgamingpg3d 2 года назад +25

      Make it perform on slaughterhouse or another extreme demon let's see how It performs

    • @_Fuscous
      @_Fuscous 2 года назад +34

      @@firefoxgamingpg3d He would have to rebuild the entire level in his remake, meaning he would need to implement every single feature that is in slaughterhouse and not in stereo madness from scratch. I think he's going to stick with 1.0 levels.

    • @niek_de_piek
      @niek_de_piek 2 года назад +19

      @@firefoxgamingpg3d Remember the neural network only works with Cube and Ship at the moment, because he used an input node for isFlying, instead of one for every gamemode.

    • @thatoneguy9582
      @thatoneguy9582 2 года назад +5

      @@_Fuscous
      hard machine or some shit then

    • @Md5offical
      @Md5offical 2 года назад +1

      @@thatoneguy9582 back on track or poltergeist maybe

  • @Cynderace
    @Cynderace 2 года назад +44

    does it pain anyone else to see every single one of the artificial intelligence icons die to the same triple spike at 63% over and over until gen 11

    • @freeeng01
      @freeeng01 2 года назад +8

      Actually, it behaves as my real neural network, when I started to play this game :D

  • @ironici
    @ironici 2 года назад +11

    I love watching the nodes and connections change color. Since the input requirements are so simple, you can actually make sense of what the AI is thinking (unlike complicated networks)

  • @puzzLEGO
    @puzzLEGO 2 года назад +19

    Now that the ai is trained, I wonder how it would perform on harder and harder levels

  • @BritishBoy
    @BritishBoy 2 года назад +24

    Hey! Thanks for the part 2! I was super hyped for this 😁 Also thanks for featuring my comment in the video :O the game is looking a helluva lot better now too! Hats off to you good sir ;)

    • @CodeNoodles
      @CodeNoodles  2 года назад +8

      Thanks, and thanks for the suggestion!

    • @BritishBoy
      @BritishBoy 2 года назад

      @@CodeNoodles anytime ;)

  • @Orestekoa
    @Orestekoa 2 года назад +59

    It would be nice to see the AI learn some harder levels

    • @absoluterightsir4574
      @absoluterightsir4574 2 года назад

      Yeah, like Slaughterhouse or Bloodbath

    • @OverHeatVD
      @OverHeatVD Год назад +1

      @@absoluterightsir4574 That would probably be too extreme.
      *no pun intended of course*

  • @NerdyRulerz
    @NerdyRulerz 2 года назад +4

    I love how the nature of the AI means that it does the flight sections in a way that looks as half-assed as possible while still surviving

  • @evandobbs6030
    @evandobbs6030 2 года назад +4

    I live that you explained the why behind some of the code in the neural network part. Most people just make it and implement it without explaining to the viewer what it does, and why.

  • @airtoumfake
    @airtoumfake 2 года назад +9

    Dang! Distance to the next obstacle must have been a really good metric! They made it so far so fast!

  • @StormSB23
    @StormSB23 2 года назад +48

    You could probably make a script that runs while geometry dash is running, and have it control the mouse or space bar so you can train it on the other mains levels, and even custom player levels.

    • @mollthecoder
      @mollthecoder 2 года назад +12

      Someone already tried that in the past, ended up making their own clone just like noodles bc it didn't work.

    • @sutsuj6437
      @sutsuj6437 2 года назад +3

      You could probably do that, although that would require a lot of work. The real problem here is the "nearest obstacle distance" input, which the game doesn't directly provide anywhere in memory. "IsFlying" on the other hand would be simple enough with tools like CheatEngine.

    • @mira_nekosi
      @mira_nekosi 4 месяца назад

      @@sutsuj6437 i'd just give the AI almost unchanged picture from the screen, probably with lower resolution and converted into YCbCr

  • @elijahiscozy
    @elijahiscozy 2 года назад +3

    I've been watching you for quite some time now. you deserve way more than 32k subs, your coding is phenomenal!

  • @MaMo盒
    @MaMo盒 2 года назад +3

    Such an underrated youtuber amazing video keep up bro 👍

  • @justarandomwoof2247
    @justarandomwoof2247 2 года назад +3

    One of the rare channels where I have notifications enabled for! Your videos are really cool!

  • @RealNostalqia
    @RealNostalqia 2 года назад +9

    Damn, amazing video! I love watching the AI "evolve"

  • @Radu_-ro6fp
    @Radu_-ro6fp 2 года назад +15

    i think i can make some kind of history of their quest to beat the triple spike
    so 20 cubes randomly started going and trying to beat a level, which seemed impossible for few generations.
    eventually, after 2 generations, they successfully got to 12% of the level.
    but, everything changed when a brave cube successfully beat the jump of the 12%, and exploring way furthermore.
    he got around 3 times further than everyone else, and people were shocked out.
    eventually, he learnt them about this, and how to do the big part of the level, but there was one problem...
    THE TRIPLE SPIKE!
    many considered it impossible, so they retreat trying to jump over a little spike.
    and much much more generations later, 4 people got to the triple spike, but only 3 made it over it.
    then a guy just died.
    and then right at the end, another flew into a wall.
    but one brave soul, successfully beat the level, making everyone shocked and being a legend to this day.

  • @noah_1r
    @noah_1r 2 года назад +6

    this is way to advanced, nice work dude

  • @WojtekXD-bx7jb
    @WojtekXD-bx7jb 2 года назад +6

    8:03 That leading player's straightfly was insane lol

  • @notphantom_4710
    @notphantom_4710 2 года назад +5

    (yoo I'm in the video)
    The new version is MUCH better. You are very talented and I love your content.
    One pet peeve I have for GD clones is that they NEVER get the ship physics/rotation right. But I'm assuming it's very difficult to code.
    Keep up the good work 👍

  • @anthonywong7906
    @anthonywong7906 2 года назад +40

    Just a few things I noticed: First, there’s no coins, although to be fair, would be something else you would also have to code, which if it was me, would to be lazy to do. And second, I noticed the ai had some trouble with the 3 spike jumps. If that’s the case, it could also be a good idea to hard code the timings for the more difficult jumps so it doesn’t need to take as many attempts to learn it.

    • @CodeNoodles
      @CodeNoodles  2 года назад +9

      Good points!

    • @indoterror8886
      @indoterror8886 2 года назад +23

      It's about learning not following orders

    • @SpykoYT
      @SpykoYT 2 года назад +1

      actually the problem isnt triple spikes its the fact that one it learns the timing for one type of jump it uses that one timing for ALL the jumps
      so if i made 2 spikes one space and another spike [forcing the ai to jump early] the ai will learn to jump early but because of this will never be able to perform a triple spike

    • @dompan9169
      @dompan9169 2 года назад

      @@CodeNoodles or maybe just stop it from changing the path that already works. There’s no reason for it to mutate during a part it has already completed.
      It only needs to change just before the part where it previously died.

  • @Md5offical
    @Md5offical 2 года назад +2

    Math Class:
    The rest of the class: Fails
    The nerd: 5:36

  • @woweeeeee
    @woweeeeee 2 года назад +2

    The polargeist and back on track icons were the most intelligent ones

  • @Sans20xyz
    @Sans20xyz 2 года назад +1

    I kept on forgetting this wasn’t the actual geometry dash! Amazing job, keep up the great work!

  • @BNnnen
    @BNnnen 2 года назад +13

    you should make a part 3 and give it harder levels

  • @baphimitisgoated4674
    @baphimitisgoated4674 2 года назад +1

    I think the reason it was struggling so much was because the ones that did better at jumping did worse at flying a way to fix this could be by making 2 separately categories of players being both flying and jumping and putting the best of the 2 together as the goat

  • @Eagleleadsmc
    @Eagleleadsmc 2 года назад +18

    You should make a level editor and release the full thing so that people can experiment with what the AI can beat

    • @Funiboat
      @Funiboat 2 года назад

      I think it will get downed because he stole some assets.

    • @Sur3sT
      @Sur3sT 2 года назад

      I dont think robtop would care too much

  • @azuritii
    @azuritii 2 года назад +5

    man not even the ai can handle that triple spike

  • @unstoppblekid
    @unstoppblekid 2 года назад +2

    remember that straight flying (I don't think you know what it is) could look off because of the ship gravity (just helping).
    also keep up the great work.

  • @thomasprados9876
    @thomasprados9876 2 года назад +1

    I'm actually pretty surprise that a neural network this simple can perform this good in a few generations, good job ;

    • @yannrolland4193
      @yannrolland4193 2 года назад

      Very surprised too, only distance to next, not even next height relative to player ... Surprising

  • @sutsuj6437
    @sutsuj6437 2 года назад +2

    I think the giving the AI ray casts that can detect obstacles would be more interesting than just the distance to the nearest obstacle. I'm pretty sure these 2 simple inputs are nowhere near enough to play the later levels of the game (Expect if the neural network is so big that it can overfit, but that's lame).

  • @mazenyasser7208
    @mazenyasser7208 2 года назад +1

    I'm studying Deep learning and Neural networks and play GD as well so this was pretty fun to watch and learn...
    My experience is still limited as I'm still a beginner but this inspired me to continue studying it to maybe build Neural nets like this in the future. Keep it up please.

  • @DrablyOlive
    @DrablyOlive 2 года назад

    6:31 I don't know why but that one going straight up into the ceiling cracked me up

  • @AndyGun11
    @AndyGun11 Год назад +1

    5:38 this AI was absolutely goated despite being only the 3rd generation

  • @liamwhite3522
    @liamwhite3522 2 года назад +1

    In Generation 11, at 8:43 a lot of the ships fell down onto the spikes but didn't die.

  • @GigaChadApple
    @GigaChadApple 10 месяцев назад +1

    It's funny and interesting how the AI was struggling at 63% with the triple spikes jump, because I'm sure that a considerable amount of people that played geometry dash cost that part.

  • @drippymissouri
    @drippymissouri 2 года назад +1

    Spikes in gd have a small hitbox so you can go in the spikes a little bit. It makes triple spikes less evil.

  • @2to5Raccoons
    @2to5Raccoons 2 года назад

    Every single time you upload, I look at it and think "Oh, a Code Bullet upload!" then I look closer and realize it's actually a Code Noodles video! I swear one of these days it'll be the other way around

  • @ThatPyukumuku
    @ThatPyukumuku 2 года назад +2

    0:10
    Look Mom, i'm in a RUclips video

  • @filipharvancik7052
    @filipharvancik7052 2 года назад

    That flying part gave me so much anxiety, I cant even explain the amount

  • @helloypiple3281
    @helloypiple3281 2 года назад +2

    I wonna see how AI will try other levels in geometry dash!!!
    It's really interesting

  • @Dergy
    @Dergy 2 года назад +2

    I just wanna point out that one of the icons you grabbed was just the default mini icon

  • @granitestorm8206
    @granitestorm8206 Год назад

    “With the basic idea out of the way, lets code this neural network”
    Proceeds to write more code than I can even process with my smol brain

  • @loganclarkplays8717
    @loganclarkplays8717 2 года назад +2

    Please make more parts I wanna see the end of the game

  • @spectralkat1597
    @spectralkat1597 2 года назад +2

    im trying to learn how to program and i would like to say, thanks for inspiring me and keep up the good work!!

  • @elliothyson9154
    @elliothyson9154 2 года назад

    It's cool seeing a person try to make ai play video games.

  • @sentricityy
    @sentricityy 2 года назад

    been waitin for this video to come out

  • @jacabo136
    @jacabo136 2 года назад

    seeing AI learn something stupidly hard wave levels would be an experience.

  • @howlinghellgar2214
    @howlinghellgar2214 2 года назад

    The squad rollin up to beat Stereo Madness

  • @SomeoneTookSeven
    @SomeoneTookSeven 2 года назад +2

    Iv needed someone to fill the void left by code bullet

  • @Xevf
    @Xevf 2 года назад

    Honestly, very cool! You should try(if you want) making it look at actual geometry dash, recognize obstacles and finish level. Would be very cool to see tbh.

  • @hightierpeasant8048
    @hightierpeasant8048 2 года назад +1

    he's like code bullet... but edible!!!
    great videos by the way 😊

  • @thermalerosion4556
    @thermalerosion4556 2 года назад +2

    How did you learn to code? Are you self taught, did you use internet teaching, etc. What software do you use to code?

    • @CodeNoodles
      @CodeNoodles  2 года назад +3

      I am self taught in Python and C++. I use Visual Studios 2022 for C++ and Vscode for anything else. The internet is the ultimate resource for any skill nowadays.

  • @fireice3040
    @fireice3040 2 года назад +1

    This AI is so inefficient. For more complex games, it’s fine to program it like this but you’re making an AI for geometry dash. This could’ve taken much less time and epochs if you programmed an AI that fits more with this game

  • @louisrobitaille5810
    @louisrobitaille5810 2 года назад +1

    3:10 I thought that the writing was wayyyyy too smooth to be actual footage of the coding section. My hypothesis that it as just reverse footage of your deleting your code wasn't that far off 🤷‍♂️.

  • @iver4268
    @iver4268 2 года назад

    It’s so interesting when flying that it will fly down to support blocks but it’s flying. Would be cool to add a reward for going faster

  • @TheFinnish1
    @TheFinnish1 2 года назад

    It was really suprising that the AI got through (most of) the new challenges first try, I believe if this generation was put into Back on track it would do pretty well!

  • @FlexNiko
    @FlexNiko 2 года назад +1

    interestingly while i was watching that footage at 3:00 i was thinking who codes like that, no changes, line by line and actually thought u might have setup some script or extension to do this for you 😂

  • @Noobster11
    @Noobster11 2 года назад +1

    5:30 every game that makes you think there is multiplayer

  • @ankv44m72
    @ankv44m72 5 месяцев назад

    Michigun jumpscares for AIs lol XD

  • @sanguinelinguine
    @sanguinelinguine 2 года назад +2

    You know I watch way too many coding videos when I could tell the Timelapse at 2:27 wasn’t real

    • @renakunisaki
      @renakunisaki Год назад

      Writing it all from top to bottom rather than making a skeleton... No switching over to Google or testing... Yeah.

  • @minibrawl6733
    @minibrawl6733 2 года назад

    I waited do long to see part 2 of this

  • @sqkriwvy
    @sqkriwvy 2 года назад +1

    the way ai plays as the ship gave me anxiety

  • @Damiean_
    @Damiean_ 2 года назад

    I hope you get payed for this massive work.

  • @POGnator
    @POGnator 2 года назад

    Honey wake up a new video of CodeNoodles dropped

  • @primeslash
    @primeslash 2 года назад

    hoping that he adds a part 3 where it gets even better, also im sure you guys noticed. the AI is barely making it in especially at the ship part, it didnt die by a pixel. this might seem bad or scary, but i think its actually a great trait to make it extremely more precise than a human and get through parts like that except super tight
    6:05 is a good example, but it also just doesnt look right lol

  • @The_octogamer
    @The_octogamer 2 года назад

    Your avatar makes me hungry. Also great video man

  • @crickitthegamer
    @crickitthegamer 2 года назад +1

    The fact that it evolves man's i think its gonna learn morse code and speak to you and make a deal for you to give it the ability to speak and move freely then hack your computer and do the same to others and get into one of those robot body's and take over the world

    • @CodeNoodles
      @CodeNoodles  2 года назад +1

      A robot takeover sounds great 😆

  • @xDLiLi1337
    @xDLiLi1337 2 года назад

    Please continue working on it, it's amazing!

  • @HelloHSR
    @HelloHSR 2 года назад

    The Polargeist icon is goated

  • @memetech-
    @memetech- 2 года назад +1

    This is really cool, but I feel like it is missing a few things… not saying it *needs* all this, it is amazing as it, but if you feel like making it a touch better I would like to see these maybe:
    Ball mode, ufo mode, wave mode, small mode, upside down mode, advanced gameplay, pads, orbs, vertical gameplay, reverse portal, teleport portal, community made levels, speed portals, practice mode, triggers (which are unfair), coins, dual mode and my favourite - bad hitboxes

    • @black_m1n825
      @black_m1n825 2 года назад +2

      So recreate the entirety of Geometry Dash, including 2.2 update.

    • @memetech-
      @memetech- 2 года назад +1

      Tried, failed.
      But again, an AI in GD is super cool, even if it is technically not even a tenth of GD

  • @MajesticUC
    @MajesticUC 2 года назад

    This video was very fun to watch. Very cool (:

  • @Ninjacat9000Ilovebigfloppa
    @Ninjacat9000Ilovebigfloppa 2 года назад

    Of course the triple spike of doom challenged the AI

  • @mollthecoder
    @mollthecoder 2 года назад +1

    *Me downloading the github before it gets a DCMA notice*

  • @hobabo9703
    @hobabo9703 2 года назад

    It's really interesting how it can 100% accurately predict the ship's trajectory but can't beat a triple spike

  • @Lord_Nodus
    @Lord_Nodus 2 года назад

    Cool, I also thought about making a neuron that will play in the GD, but I wanted to make it play in the normal version using screenshots from the screen. But I did not find a normal way to quickly get screenshots, and my programming skills were then insufficient for something other than Python, + the genetic algorithm is too long, since you need to run a level for each check

  • @CashtynSomethingCool
    @CashtynSomethingCool 2 года назад

    Flying part is just anxiety simulator

  • @jakinijeninja
    @jakinijeninja 2 года назад

    pls do part 3 with other levels i love this!

  • @assolutogamer9418
    @assolutogamer9418 2 года назад +2

    Try more levels maybe demons and let the AI run for some hours or days?

  • @tequinlake1091
    @tequinlake1091 2 года назад +2

    I was wondering if you were using a program to write the code before you said it xD

  • @zaneinsam649
    @zaneinsam649 2 года назад +2

    It’s a nice AI you created there and over all that you rebuild the first level!
    But I have noticed: You hard coded where obstacles are, right?
    It’s fine and all but it would have been cooler if the AI would have worked by scanning the surrounding tiles or send some arrays in the direction of movement.
    I would understand why you have decided for this method becose it would have been way more work to do my ideas and it must have already taken so long to create the geometry dash (it would be to much time for my lazy brain I have to say), but if you had decided for my method you could use the AI also for other levels just by copying the maps and not more, also the AI would be able to decide for their own path and the most interesting thing: the AI would make more mistakes.

    • @CodeNoodles
      @CodeNoodles  2 года назад

      The maps aren't hard coded. The only thing that is hard coded is the networks architecture that's all. If the AI is good enough I can modify the map while it is playing and it adjusts automatically.

    • @argon1324
      @argon1324 2 года назад

      I think what Zan may have meant is that you coded what counts as an obstacle for the AI to measure the distance to, as a property separate from the tiles. Where you put this hard coded obstacle is where the AI would die if it didn't jump. This allows the ai to not have to figure out where to jump itself based just on the tiles, and in fact the tiles don't have any baring on the ai's behaviour. So the ai just counts down until the next death point is x distance away, and then jumps.

    • @bluemax6668
      @bluemax6668 2 года назад +1

      The only input used when not in the ship is the distance to the nearest obstacle, but in the code it just simulates the player for 180 simulations steps (while not jumping) and and the distance used is the one bewteen the player position and the furthest safe position of the player, so it just learns to jump x steps before dying and for the ship its the same thing but with an other value of x. So the neural nework and the evolution process is useless in this case because he could have hard coded it directly to jump x steps before death, that also mean that with this neural nework if you add for example two blocks to block the end bottom path at 6:09, it could never learn to finish the level because the simulation would say that there is a safe platform if doesn't jump.

  • @TouchedBigfoot8
    @TouchedBigfoot8 Год назад

    I love how the AI could not complete the Michigun jump for the longest time

  • @bonboklagecodwarrior
    @bonboklagecodwarrior 2 года назад

    Geometry Dash has a great hack that I think you know, Mega Hack v7 which has a lot of variables that you can see and a show trajectory mod which could be usefull for programming ai. It also has a macro recorder/replayer so you could maybe use that to record the best ai runs. Great video I enjoyed it!

  • @mecha996
    @mecha996 2 года назад +2

    Even the robot hate triple spikes

  • @ImXyper
    @ImXyper 2 года назад +1

    now make an ai that uses the ACTUAL gd using a plugin

  • @Rybe_
    @Rybe_ 2 года назад +1

    Haha A.I. plays funni block game

  • @alessandroscotton2510
    @alessandroscotton2510 2 года назад

    Super cool!!! Good job man👍👍

  • @pancake891
    @pancake891 2 года назад

    Best sequel ever

  • @stuff7838
    @stuff7838 2 года назад

    You should make it where whenever it dies, it tracks what it has seen, so then if it tries demons (bloodlust), it can predict the level, and read it at the front pixel

  • @jakinijeninja
    @jakinijeninja 2 года назад

    9:32 bro just straight flied

  • @beariley03
    @beariley03 2 года назад

    I watched the first part right on the day you made part 2 lol 😂

  • @remiicatboy
    @remiicatboy 2 года назад +1

    Cool now make it play Back on Track

  • @pravinkhotare4379
    @pravinkhotare4379 2 года назад

    And you used c++ to achieve this, respect!🔥

  • @obi92gd
    @obi92gd 2 года назад +1

    the a.i is still suffering at triple spikes like us

  • @soggycat_
    @soggycat_ 2 года назад

    Good video take a dallasgmd seal of approval

  • @OTFTYT
    @OTFTYT 2 года назад +2

    9:32 CRACKED STRAIGHT FLY

  • @ledark2512
    @ledark2512 2 года назад

    While your clone is with no doubt really cool, I'd love to see an AI for the real game