@@c0zmozys yeah but that neural network hadn’t evolved and adapted to the level yet, meaning that A.I., without evolving, still had more skill with only the knowledge learned from completing Poltergeist, Back On Track and Stereo Madness, tho i do get it, those levels provide with everything you need to pass Dry Out other than the basic upside down part
Lol you think this how stuff is made, neural networks require a lot of calculations and mathematical equations and calculus, you are talking about simulating an entire brain with gradient descent and back propagation algorithms, it's not only distance to next obstacle, he might have said that to make things simpler for viewers or else he wouldn't require any machine learning algorithms,it's more complicated ma friend.
@@cinemacat4108 dude you can see the node slowly turn red the closer it gets to an “obstacle” (which I think he just marked all the obstacles as what it needs to jump over lol)
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 🤙
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
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
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.
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
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.
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
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.
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
ahahahahahahahahahahahahahahahahaahaahahahahahaaaaaaaaaahahahahahahaahaahahahahahahahahahahahahahahahahahahaahaahahahahahahaahahahahahahahahaahhaahahahahaaahaaahahahhahahahhahahahhahahahahahahahahahahahaha get it? because its impossi-
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)
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.
Oh wow the AI fluked Dry Out - not to mention the couple of seconds of perfect straight fly. I reckon this could be trained to beat demons tbh - with the issue being you'd need to make said demons. Is there really no way to get your AI to work in the real game, because that would be really cool.
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.
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
Please make this record the series of inputs given for the final result of each level so they can be ported into another software that can replay them in GD and also try more difficult levels like Clubstep
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
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.
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 :)
Those neurons are called hidden neurons. They don't represent any of the inputs to the network but rather act as another layer of computation for more complex behavior. They take in the outputs from the input neurons.
I do have to wonder how much of this is the AI actually knowing how to play the game well and how much is just using AI to essentially bruteforce the correct inputs.
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)
Bro people with 100s of thousands of subscribers be making 3d games that are terrable and look terrable ,while this nigga be making a while ai , just because ,higly underrated
The way the AI handles the ship never fails to make me nervous
Same
Imagine a video of just the ship entitled "All your anxiety in one video"
@@KryllyxOfficial Hehe, lol.
Same
It’s like cube but flying
The AI passing Dry out in the 1st gen is amazing.
did better than i have and i have done it over 100 times
@@landon2plantsyoure a human and its a neural network. do you see the difference here?
@@c0zmozys yeah but that neural network hadn’t evolved and adapted to the level yet, meaning that A.I., without evolving, still had more skill with only the knowledge learned from completing Poltergeist, Back On Track and Stereo Madness, tho i do get it, those levels provide with everything you need to pass Dry Out other than the basic upside down part
@@c0zmozys we also have neural networks in out brain
@@DeamonDragoon yes the reason AI has neural networks too is because it’s supposed to be mimicking intelligence/ humans
Funny how “once distance to next obstacle is close -> jump” is really all you need to do the majority of the level lol
well, most of these beginner levels are just piss-easy timings, no fakes, no complicated parts with orbs etc.
Lol you think this how stuff is made, neural networks require a lot of calculations and mathematical equations and calculus, you are talking about simulating an entire brain with gradient descent and back propagation algorithms, it's not only distance to next obstacle, he might have said that to make things simpler for viewers or else he wouldn't require any machine learning algorithms,it's more complicated ma friend.
@@cinemacat4108 dude you can see the node slowly turn red the closer it gets to an “obstacle” (which I think he just marked all the obstacles as what it needs to jump over lol)
@@cinemacat4108 🤓
@@cinemacat4108 what do you mean by simulating an entire brain? You can see the entire neural network in the top left.
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 🤙
Thanks for the suggestion!
@@CodeNoodles I am also guessing you have seen "Code Bullet" and how he does his videos considering you use a similar style and soundtrack to him.
@@theautonomous the "soundtrack" is just non-copyright music, not really super interesting that he uses songs that sound similar
@@Solutra true lol never occured to me.
You should totally add the coins
Watching AI learn their path towards multiple objectives would be cool
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
Waiting for part 4 when you just recreate the entirety of geometry dash
ai beats vsc
AI beats Bloodlust
AI beats TON 618
@@jwjustjwgd woah no way an ai can beat the biggest black hole
@@zahrannahyan9666 that was a joke right
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
its not on the tip but more of around the middle
And also robtop squishes the spikes in a little, to make it easier
@@undefined06855 only on one triple spike in stereo madness
@@brandonoverbey6948 i know it also happens on cycles
@@brandonoverbey6948 every triple spike in the robtop levels is squished in
I can’t believe he was like “more?” And we said “More!” And he went “MORE!” AND GAVE US SO MUCH MORE STUFF
crazy how ur able to upload so frequantly with this high quality videos
Thanks so much 😊
@@CodeNoodles remember me when you get famous
Yeah :D
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
i see you everywhere
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
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.
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
No, thank you!
@@CodeNoodles fu-
AI Warehouse has infrequent but great AI content
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.
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
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.
The music syncs perfectly with dry out, I am at peace
I love how much better at Geometry Dash the AI with 8 brain cells is than me.
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
This AI Beat back on track in 59 attempts, Im scared of what it can do...
ahahahahahahahahahahahahahahahahaahaahahahahahaaaaaaaaaahahahahahahaahaahahahahahahahahahahahahahahahahahahaahaahahahahahahaahahahahahahahahaahhaahahahahaaahaaahahahhahahahhahahahhahahahahahahahahahahahaha
get it? because its impossi-
1 year later still cant figure out how to work this
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)
7:18
Damn, this AI plays like everyone.
i was always going up
@@doshi6311 up is for the coin
Same icon beat both back on track and poltergeist, he is an MVP
certainly
Part 10 : AI Beats Clubstep in Geometry Dash
love ur job btw
I feel like at this rate, it's suitable for part 4
I hope your channel blows up. These vids are fun to watch
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
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
that one guy: decent enough. time for bloodbath!
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.
I can't believe you just made a new version of Geometry dash! amazing!
next you need to take the keystrokes and see if the actual level works. :) love your vids btw
Oh wow the AI fluked Dry Out - not to mention the couple of seconds of perfect straight fly. I reckon this could be trained to beat demons tbh - with the issue being you'd need to make said demons. Is there really no way to get your AI to work in the real game, because that would be really cool.
This ai beats the levels faster than most real people that play the game
Yeah and it handled upside down gravity like nothing lol
i hate how it always cuts it as close as possible in the ship parts
bro yessss my favorite geometry dash UA-camr bro ur so good
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?
Do you think it would be easier to just try and integrate the bot into the actual geometry dash?
probably not since its made specifically for this clone and he doesnt have Gd's source code so he can't exactly do anything about that
Your hard work and productivity is amazing!
Discovered this channel recently and I love it
Absolutely my favourite series :DDDD Great job CodeNoodles!!
Making the A.I play Bloodbath when?
Imagine it learning how to do blood bath or even better slaughterhouse that would be amazing
Or even better tidal wave 😂
I loved all 3 videos so much, keep the good work!
Cool! Now make the ai beat bloodbath
wow, adding that vertical collision detection really improved things, huh?
I find videos of AI doing perfect runs very relaxing
Up next: Can an A.I beat Slaughterhouse?
I hope it will happen
Up next: Can an A.I. beat sonic wave
The AI finding the most dangerous way to complete the ship:
*Walter White cooking GIF*
now, make it pass slaughterhouse 💀💀💀
Can you add a README file to the GitHub page or post a tutorial on how to download it?
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.
5:20 Has anyone noticed how this part syncs with the music?
I've been waiting for someone to do this :)
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
At this rate you'll have them beating Sonic Wave while I'm still stuck on B.
Nice music taste
Please make this record the series of inputs given for the final result of each level so they can be ported into another software that can replay them in GD and also try more difficult levels like Clubstep
yeah but the problem is that the physics isn't exactly the same, so porting it over to GD would have problems
@@aadenboy True but im sure they could be refined enough to work for most levels
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
Bloodbath?
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!
You'll be famous if you continue with this project man
I feel like he's nearly reached the end of the things he can do in this series
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.
Yay New Ai Teaching Geometry dash Video
The fact a clone of the game is needed for this just shows how amazing RobTop's coding is
no it just shows that you cant easily extract the source code of the game
you should reverse the rotation of the cube in the reverse gravity section to make it seem more natural
In the next part you might want to reverse the cube rotations while inverted.
If you ever make a new part, that is.
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 :)
11:20 seconds how do you do dis though all i see is files): i wanted to try this...
now make it beat bloodbath
Idea: Create a skilled Ai on more complex things (blue orbs, ball gamemode, etc) and try to let it beat insane levels like xstep.
1:20 void sprinkler
1:22 pee pads
1:26 confetti sprayer
if you made it one, not multiple AIs and removed the lil gui at the top left, i would be convinced that that is real geometry dash :O
That's what I was going for!
@@CodeNoodles yeah! it is very convincing
that's pretty cool. it's a pity that there are only two game modes, whereas in the original there are 7 of them
Nice ! Now lets see if it can beat Clubstep and Deadlocked
Why is no one talking about how the icons rotate backwards when jumping in flipped gravity
Because everyone sees it
@@danielyuan9862 but it’s so painful to watch
now make it beat slaughterhouse
Hi CodeNoodles,
Awesome video! I wanted to know what those middle hidden neurons are composed of.
-Thanks!
Those neurons are called hidden neurons. They don't represent any of the inputs to the network but rather act as another layer of computation for more complex behavior. They take in the outputs from the input neurons.
If you manage to implement it in the real geometry dash it would be epic
You should get the ai to try doing straight flys
Okay
*Now make it do Bloodbath*
A.I.:
- first generations are Chad's that do half of the level at the first time
-give heart attacks to the viewer while flying
I can't wait to see if the bot can play Slaughterhouse
funny how the ai straight flys so well. xD
Nice! Time to watch some anxiety inducing flying!
:D
I do have to wonder how much of this is the AI actually knowing how to play the game well and how much is just using AI to essentially bruteforce the correct inputs.
Jumping when you're about to hit a spike is pretty easy to brute force.
imagine how funny it would be if he made a part 4 and he made the AI play slaughterhouse
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)
cool
now make it do bloodbath
Why are all of the cubes useless and die after 2 seconds and then theres always one cube thats absolutely cracked
Lets go, new upload
Day 3838 of waiting until AI completes Tidal Waves
You are that one guy that would be able to make a fully working AI in the actual game.
With triggers
In the Grand Finally (wink wink) the AI should learn clubstep
Me waiting for him to make Clone-Deadlocked and makes the AI grind for days
This is really cool, but you should make it do Clubstep next.
Bro people with 100s of thousands of subscribers be making 3d games that are terrable and look terrable ,while this nigga be making a while ai , just because ,higly underrated
Every video of you makes me hungry like fr that bowl of spaghetti looks SO GOOD 😆😭