The way the AI handles the ship never fails to make me nervous

The AI passing Dry out in the 1st gen is amazing.

Funny how “once distance to next obstacle is close -> jump” is really all you need to do the majority of the level lol

You should totally add the coins Watching AI learn their path towards multiple objectives would be cool

Thanks for your hard work! I have a suggestion: To help improve watch time of your videos, commentary during periods where the AI is “training” may be helpful. I do not make videos but it is something I have seen in the past, so feel free to take it with a grain of salt. Keep up the good work 🤙

Waiting for part 4 when you just recreate the entirety of geometry dash

I can’t believe he was like “more?” And we said “More!” And he went “MORE!” AND GAVE US SO MUCH MORE STUFF

This really shows an interesting point in neural net development. If you use inputs that are extremely bimodal where it's nearly always in its best interest to act one way or another, the AI very quickly tunes it correctly! I think having the vertical check was very useful because in nearly all situations it is a bad idea to jump when something is above you. It is also nearly always useful to jump when an obstacle is directly in front of the player. It's really interesting to see how the AI nails this game once given the proper tools to succeed! Thank you for sharing this

The reason its hard jump over triple spikes in your game is because the actual game's spike hit box is a small square that's on the tip of the spike

My favorite part was when he said “it’s code’in time” and programmed all over the place

i thought the series ended. good that they did not edit: it would be awesome if you could release this project as game so we could experiment how the AI would try to straight fly (it does ship parts really weirdly compared to normal GD bots) 8:36 yellow portal is really weird when rotation is not changed 9:00 transition perfectly syncs edit2: i did not watch whole video before commenting lol

crazy how ur able to upload so frequantly with this high quality videos

Would also be interesting to see how the ai behaves if it doesn't get reset after each level, so it could truly be learning

Literally saw the 2, video before 10 minutes on my start page… pressed the subscribe button and then… CodeNoodles uploaded a new Video. I very like these Videos pls do more of AI and Neural Network Coding. Thank you

8:13 This is interesting. The neural net and task are so simple that one of the randomly generated nets of the starting pool was able to just do it first try. That's pretty dope.

Absolutely my favourite series :DDDD Great job CodeNoodles!!

I love how much better at Geometry Dash the AI with 8 brain cells is than me.

I loved all 3 videos so much, keep the good work!

I hope your channel blows up. These vids are fun to watch

The music syncs perfectly with dry out, I am at peace

Discovered this channel recently and I love it

Your hard work and productivity is amazing!

I think it would be interesting to see how the AI from one level reacts to a different level. While they are mostly the same mechanics, in theory there might be some differences. Maybe a round where all the successful AI are brought into a brand new level and then see if they all win still. Ofc not saying you need to do it if you are done with the project, but I think it could be fascinating.

Cool video! I wasn't expecting it. What would be cool though is if they had coins. Like in the generation after it (if there even is one), they would try and get the coin, because they would be awarded.

7:18 Damn, this AI plays like everyone.

next you need to take the keystrokes and see if the actual level works. :) love your vids btw

If you make further parts I think it would also make sense to try making a level as hard as it can possibly go in this clone

CodeNoodles is a secret agent working for noodle companys because every time i watch a video i get insainly hungery and i am currently boiling water to make ramen... thank you

Same icon beat both back on track and poltergeist, he is an MVP

Please continue this series until the ai beats bloodbath, also I think you should commentate on the ai's progress to make the video more entertaining

I can't believe you just made a new version of Geometry dash! amazing!

Do you think it would be easier to just try and integrate the bot into the actual geometry dash?

I've been waiting for someone to do this :)

the sync in back on track is sick!

how an ai can be better than me in dry out :( nice video man, you need more recognition, your videos are too good!

I know a part 4 isn’t needed, but I think watching the AI figure out how to play a memory level would be cool. Something as simple as 3 paths and only 1 can let you pass or something a little more complex like the level marathon. Great video 👍 Edit: I did not watch the whole video before commenting

Is it possible to put the winning AI of each level against each other to see which one can adapt the fastest to new levels?

The AI finding the most dangerous way to complete the ship: *Walter White cooking GIF*

Nice! Time to watch some anxiety inducing flying! :D

Yay New Ai Teaching Geometry dash Video

This AI Beat back on track in 59 attempts, Im scared of what it can do...

Hello, could you clarify something for me? So I don't know if I understand backpropagation well enough, the thing I currently doing is for every layer i--: for every weight i--: //output = neuron that the weight contects to A:= -(target[i]-output) B:= output*(1-output) //for ReLU C:= neuron that the weight coming from weight -= Learningrate*(A*B*C) bias -= Learningrate*(A*B)

Every video of you makes me hungry like fr that bowl of spaghetti looks SO GOOD 😆😭

Nice ! Now lets see if it can beat Clubstep and Deadlocked

This ai beats the levels faster than most real people that play the game

I find videos of AI doing perfect runs very relaxing

Hi CodeNoodles, Awesome video! I wanted to know what those middle hidden neurons are composed of. -Thanks!

bro yessss my favorite geometry dash KZfaqr bro ur so good

A problem I noticed, I play GD a lot, and if you make a part 4, would you be able to reverse the way that you rotate when you are upside down, the jumping and rotating while upside down makes me... eeeeeeeeee

do you mind releasing this project so we can experiment with it and watch how it will perform on harder levels?

How did dry out and the background music have quite good music sync at times?

Can You add effects to the jump pads and orbs?

This is really cool, but you should make it do Clubstep next.

that one guy: decent enough. time for bloodbath!

is there any way you can make this for real gd? if so that would be insane (this is already really cool tho)

This is awesome 👏

try adding in the coin paths for the levels (you don't actually need to add the coins). i think it'll be interesting to see if the ai goes for it or no

You'll be famous if you continue with this project man

it would be amazing if you could train your AI on your clone and then hook into the real game and play the levels with your pretrained network for part 4 :)

Lets go, new upload

I wanted to use the level editor but it feels very tedious. You can only grab the tile you are hovering over and cannot cycle through the titles, or at least I can't find a way to. Is there a button for cycling through tiles?

Hello I would like to know if it's possible to create an AI which read the screen in real time, like this we don't need to create a geometry dash clone but use the "official" version ?

Part 10 : AI Beats Clubstep in Geometry Dash love ur job btw

can't wait to put this against acheron

I'm actually not surprised they beat Dry Out on the first generation. The AI always seemed to either get really good, really fast, or get stuck on one part for a while (like in the first level)

Very cool stuff Quick question: if we record the AI playing a level and want to show it to you, how would we do that? Do you have a Twitter we can tag? Maybe a community post we can link videos in the replies to?

I thought it's gonna be in the real game but this is still awesome

Making the A.I play Bloodbath when?

yay finally a new part!

you should reverse the rotation of the cube in the reverse gravity section to make it seem more natural

wow, adding that vertical collision detection really improved things, huh?

cant wait to see it pass slaughterhouse and limbo!

How did you make the glass library? I have been wanting to make my own library but I just can't figure out how

I’ll be honest I want to see this beat a level such as clubstep, but that could lead down a rabbit hole. Who knows it might lead to it beating slaughter house, but that would take a lot of work on your side.

Can you add a README file to the GitHub page or post a tutorial on how to download it?

Could you train the AI based on your gameplay? Like you play a bunch of times and the AI learn from you

I'd love to see it handle a demon level after all that. Maybe without all the fancy graphics, but seeing it overcome a really hard level would be very fun to see.

is there a tutorial on how to make a map?

Can you do the other levels now?

i think you should a another node that is just jump pad instead of considering it an opsticle if you even said that i could have misheard you or somthin idk also i think more hidden layers could help idk tbh

noy try time machine (lets see if a AI is smarter than me XD) also great vid

Geometry dash saves its levels as a text document with some sort of encoding, people have been able to decode it into making it usable with code, is there a way you can make it so you can port a level over with just the level information? instead of having to make it manually.

To make making the levels easier just make it so you can copy the levels from the game and drag them into your own version or have an external program change the files to the correct files to transfer the levels just to save you time

Now add a neural network to make it alto adjust and learn every time it misclicks as well as letting it know when it has less than 10 seconds left on the clock so it heightens the accuracy req to not misclick then.

I can't wait to see if the bot can play Slaughterhouse

5:20 Has anyone noticed how this part syncs with the music?

Question, Why did you have to recreate the whole game, and not just make play the AI with a space bar input on an emulator of geometry dash?

At this rate you'll have them beating Sonic Wave while I'm still stuck on B.

This is actually so cool

Is it possible to make an ai that all that it knows is that it can click, hold, release or not click? And just have a general visual input of the game with no more information? Like an ai that simply sees the level and has as a goal to get as far as possible, but doesn't know anything else, that has to figure out how everything works including jump orbs, pads, the ship, etc. IDK about coding or programming AI (or coding in general lol) so idk if it would be simpler or harder to make the ai being able to just see the entire screen and nothing else and go just with that information and learning from there. It sure would take way more time for the ai to learn to play, but I think it would be even more interesting. And yeah I know, that's very impractical but that would be very interesting to watch.

You should make AI to learn some extreme demon. That would be amazing!

In the next part you might want to reverse the cube rotations while inverted.

1:20 void sprinkler 1:22 pee pads 1:26 confetti sprayer

Would be cool to see how it handles player made levels

Idea: Create a skilled Ai on more complex things (blue orbs, ball gamemode, etc) and try to let it beat insane levels like xstep.

that's pretty cool. it's a pity that there are only two game modes, whereas in the original there are 7 of them

I'm waiting till it can beat firework. Also good job I could not learn this in a millon years

You could probably do this in geometry dash itself. There are some open sourcing projects for it and the modding community is very large, so maybe try doing this in the actual game?

Cool! Now make the ai beat bloodbath

It would be cool to see wave mode