DESTROYING Donkey Kong with AI (Deep Reinforcement Learning)
Вставка
- Опубліковано 21 лис 2024
- Go to brilliant.org/... to get a 30-day free trial + the first 200 people will get 20% off their annual subscription.
Second Channel: / @codebulletsdayoff582
Twitter: / code_bullet
Patreon: / codebullet
Discord: / discord
Art created by @Dachi.art / dachi.art
There is nothing more terrifying than when code works the first time immediately. How can we know it really works if we don't spend hours fixing the bugs?
"The code works flawlessly first try" is what happens to programmers when the world turns upside down.
Spoken like a true unit-test averse programmer!
Learn test-driven development. Then you will be surprised if it doesn't work immediately.
@@jimmyhirr5773 believe it or not. Tests are also written with code. Which can also have bugs!
It happened once to me, I tested it like 10 times and it seemed to just work, it was for an assignment and honestly I just took that gift from the gods and it only had to work once more for the tutor to grade me and it did :). Honestly I don't know if I was just lucky it work 11 times in a row or it really actually just really worked first try.
As a wise man once said: “if your code works perfectly first try, it didn’t, you just haven’t noticed what’s broken yet”
I have never heard so much wisdom in a single sentence.
Truly inspiring
And you probably won't until you start testing the thing you needed it for 3 phases down the line, so it'll take you extra long to find where it is. Also with the collective luck of all people involved, it's a single misplaced negative
As a wise man once said: we don't talk about the last video
I once coded for 2 weeks without access to testing it, and had it working perfectly in 5 minutes. In my entire career this was my proudest moment.
That whole "Ground? No." bit was painfully accurate to the game dev experience.
this 100%
No fucking way 345+ game devs are watching this...
Very relatable to my experience with "gamemaker5&6" in the early 00s.
And that program should've made that whole process way easier.... 🤣
Collision in general is stupid hard to do from scratch. Unity? Kinda hard. Unreal? Less hard, I guess. Game maker? Still kinda hard. Even in my own custom made game engine, its way easier but…. still kinda hard :|
Or maybe Im just really bad as a programmer, who knows
@@syntex3664 Because that's the thing with programming, if you somehow made something work the first time, you should probably visit an exorcist.
Now make a Donkey Kong AI that learns the best barrel throwing strategies and pit them against each other for eternity
But that was the first version of Donkey Kong he made, it threw infinity barrels.
@@dreemurrdelm7865 just give the ai a reload time so it can't spam
give the barrels ai so they know when to climb and not climb arrows to fuck up with the mario/player ai
ladders not arrows*
Go full GAN. 2 AIs, DK and Jumpman trapped in never ending combat with eachother.
I love how the second AI effectively decides to become a challenge runner by removing the part of it's brain responsible for jumping, just because it could-
Now let's make it do it coinless.
why did you put a -
@@sketchystreet1 Force of habit.
@@InkyDustMan ok
@@InkyDustMan youtube commentor moment
Every code bullet video is an event that should be treated with utmost respect.
Which is why none existed in 2021.
I can't be the only one getting blackout drunk for these?
this guy gets it
best of code bullet 2021
best youtuber in 2023
When you mentioned the jumping, or absolute lack of them doing it in NEAT, I instantly had a vision of you adding points for jumping over barrels and the AI dudes going balls first sailing back and forth over the barrels instead of going to the end. Just racking up massive points for themselves over and over again.
This
@@gabribotha2403 Subscriber place
#selimtune
ah, I see that you have done that... Ima kick you in the balls
Who needs a princess when god gives you testi-tickles
Neat detail I noticed that wasn't brought up. At 2:46 you can see the player square falls all the platform a bit early, when it's only halfway off, which causes it to clip into the floor a bit. This is because the "laser" vector that detects if the floor is there is positioned in the middle of the square, and therefore doesn't detect the ground when the square is only halfway off.
This is silently fixed at 2:58, where the square now only falls when it's fully off the platform. As you can see, the lasers are on either side of the square, making sure both have to be off the platform before it falls.
Calling it a NEAT detail is a little confusing but yeah, I also noticed that
probably neat how they realized it @@barni_7762
Code Bullet is kind of like an A.I himself. In his videos he get slightly more competent over time
Well, we did design them to mimic humans
Well, he is training a neural net...
Its called learning over time
now he just needs to code in some better jokes
This is hilarious 😂
I absolutely love how accurate you show the process of coding, just fail after fail until somehow it works and you’re not really completely sure why but hey it works so it’s all good
Well have seen same yt creator's that show failures more regularly and everyone is doing good but CB is the master of this discipline and his very loyal sub show us that
There’s a Russian anecdote which, in translated form, goes something like this:
« Dad, why does the sun go from east to west every day? »
« East to west? »
« Yes »
« Every day? »
« Yes »
« I don’t know son, but better leave it alone »
It’s a stupid anecdote, but one of my favourites when it comes to programming
There's test-driven development, where you write a test for everything that should and should not happen, e.g. jumpman jumps at least once per game, and over time more tests pass. It's a lot of work, but the benefit is it will catch regressions; as we see here when Jumpman sometimes flies into the air after Code Bullet thought he'd fixed gravity issues.
@@skierpage I'd love to be able to apply TDD to game development, but the number of states and the non-deterministic means of reaching those states most games have means that you end up with very, very low coverage of the code base and/or end up pointlessly testing third party code. I've seen fat too many "tutorials" where the speaker just tests engine code
and then it suddenly doesnt
as an Artificial Intelligence Engineer, I can confirm we tickle the balls of the reinforcement learning agents as a reward function. Its one of the best ones out there.
No ML engineer would call himself AI engineer.
@@pw7225 correct, but the name of my university department is "Artificial Intelligence Engineering". i live with people who call themselves prompt engineers, soo who gives a fuck XD
@@pw7225 so no ML engineer understands set theory? :p
@Repent and believe in Jesus Christ i am just thinkin, that there is a religious programmer out there who uses all the resources he can to influence people on youtube comments without making a youtube video. He releases all these bots here expecting people to let go of their beliefs and follow Christianity. If he could give all this effort into philosophy and science, he would become an atheist
@@fizipcfx or an 'alternative scientist'
The jokes and screwing around in the first 4 minutes got you a new sub. The "breath of fresh air" bonus is how you're not afraid to swear and genuinely enjoy what you do even when your code doesn't work.
I do not know. I love codebullet, but this video feels over the top, for me hard to watch, almost cringy, and weaker than usual in the technical part.
Despite your hatred of explaining, you did an amazing job defining and explaining each AI algorithm…while not simultaneously putting me asleep in the process. Great video and always very entertaining! 🔥
I agree, I leanred more from code bullet than high school
Code Bullet really is the best inspiration. He doesn't hide or gloss over his mistakes and in so doing shows that coding really is a perpetual state of learning through trial and error.
And then promptly forgetting everything while we binge our next dopamine fix instead of working.
Seriously though, I really appreciate that you include the struggle of being human in your videos. It makes them so much more relatable.
Not to brag or something, but.... I'm not sure that it is that hard unless you learned something. Floor not working is sort of close, but not for THAT long
I was half expecting your "AI learns to run" videos to be the only two videos in one year.
Good for you to have another one. And us.
13:38 Code Bullet is so good at coding, the AI felt necessary to learn speedrunning!
I love how you somehow have the most inconsistent upload schedule, it takes you hundreds of attempts just to get code right per episode, and yet somehow you also have 2.7 million subscribers. Congratz!
It's fare to say he got these subs when he was more regular
@@heavenstone3503was he ever really regular though? Even when he was posting more often the upload schedule was still pretty erratic
Subscriber place
#selimtune
@Heavenstone long time subscriber, he's never been consistent. He's always had the charm though!
@@heavenstone3503 cough enigma machine part 2
Code bullet explains his coding better than my lecturers does and that’s saying something
he takes your understanding of it seriously.
it's the dick jokes, they help
@@aidanb7782dick jokes explain more than any PowerPoint slide could
@@aidanb7782
Like 22:02 lol
Well he is paid to so makes sense. Oh wait…
PPO is basically strapping the AI to an N-dimensional sled and punting it down the N-dimensional hill. You need to choose how big a sled to use, how much momentum to conserve, and even how the hill looks like. And in the end when you think you reached the bottom and looking for an N-dimensional cable car to take you up for more you find out that you are in a shallow N-dimensional depression somewhere half way down the N dimensional hill. Where N is the amount of weights you are using.
That's just gradient descent mostly, not really specific to PPO
I love 150 dimensional sleds on 150 dimensional hills, but it seems like a pretty good anecdote
@@MaxLennon but the gradient descent is used to find the most optimal values for a neutral netwerk
@@maartenbeute6742 yes but PPO is a specific algorithm describing how to leverage a neural network (actually two neural networks), so just describing how to fit the parameters of any model doesn't tell people very much. The method above could also be given as a description for how to do linear regression, for example. Or image classification. Or basically any machine learning task.
@@maartenbeute6742 If you want to see how an explanation of the actual algorithm would look, this link should take you to my other comment where I explained it:
ua-cam.com/video/ovIykchkW5I/v-deo.html&lc=UgxFRqioM8iaM4rJvs54AaABAg
I really love when you go into the more technical side of things, and still blending in the comedy. Great video!
Less than a minute in and he's already killing clones, and he's also learned and used a silenced gun too, this is definitely gonna be good
Imagine a Code Bullet Bingo with those stuff lol
@@hayond656 dear God that would be hilarious
13:54 it was short lived
Code bullet is probably the inner voice every programmer has while working on projects.
As a software developer by profession,
Yes.
This is precisely how it sounds
The swearing is especially accurate. I curse every single entity imaginable, mostly my computer and myself and anyone who dares to message me at the time.
esp the little part of him that goes 'hey let's use someone else's code for this'
@@sjs9698 “I’ll ask chatGPT” has also become a voice for me
code bullet is the devil on my shoulder
You mentioned the RNG involved with the barrels, but fun fact about the OG donkey kong. Whether a barrel goes down a ladder or not is based on where the player is and what direction they are facing so you can actually control when the barrels go down ladders, which would have been cool to see how the AI learns to manipulate it
Also a huge pain in the ass to code so who knows if it would have been worth it
Also would have been interesting to see how the AI would coupe with a four way joystick. You can't turn and travel on ladders. But that's beyond the scope CB is at ... For now.
@@trim7911 the AI can use an 8 way joystick if it's Billy Mitchell.
@@alaeriia01 lmao
The Jon Bailey cameo is the crossover I didn't know I needed.
CodeBullet still having to watch tutorials on the most simple thing start to become more relatable the further I get in my software studies
He first learnt the whole AI thing and then went for the 2d sprites.
This man is on another level.
@@HRIDOYKHAN-he7ss What? Can you do English?
@@jebclang9403 hey so what if they can't? don't be mean - this is one of the few chanels on yt where the comments aren't lethally toxic.
I like how nobody really forgets about the Enigma machine even after 5 years
Evan is such a nice guy, always keeps his promises, especially Enigma Machine Part 2
@@nubbyboi6523 Yeah, he'll probably make it in the next...millennia.
@@GooberInternet Better than his normal upload schedule 💀
@@nubbyboi6523Wait until it’s 2068
he already made it, but you need to decrypt his message to get the url
The square refusing to fall off after crossing the ledge unless it "looked down" was some real looney tunes stuff haha
I couldn't believe a coding channel with nearly 3M subscribers has to deal with the exact same shit as I did when I was really into Game Maker in my free teenager time
@@kelleroid are you new to this channel?
@@sebastianredden7577 Nope, just finally saw a moment I could very strongly relate to
Subscriber place
#selimtune
As much as CodeBullet struggled, it was still impressive once he started driving over those ramps with relative ease near the end. Couldn't ask for better entertainment. The part where he made an AI was cool too.
DONKEY KONG?
You surprise us with the most varied yet entertaining video games to let an AI learn.
Thank you
I didn't expect him to make a donkey kong AI tbh.
You have no idea how big my smile is! To some how just stumble onto what will now be my favorite channel?! An amazing feel. An almost AI generated feel, cause it's unreal! ....Carry on!
I'm quite impressed with the second algorithm (NEAT). That algo figured out to ignore a couple of the inputs, generated a tiny net with only 3 nodes across two hidden layers, and was beating the level without hitting the jump button. Say what you will but I'm more impressed with that than the last algorithm.
Awesome video!
Yeah, NEAT is pretty neat... (*groan*) One problem with it is that it often throws away good solutions because the mutation can often be quite aggressive and throw out long-term positive traits for short-term gains. That said: This is literally how real-world genetic evolution works too. So for this algorithm, it pays #1 to have bigger population sizes, #2 to be careful about your mutation rate, and #3 to give it enough time to run. In all experiments I did with it, it often reaches a plateau where not much happens for many generations, but after a long time, it suddenly starts improving again. I'm pretty sure it has to do with the "species" system it uses: Often, one species is so good at what it does, that even "geniuses" in other species don't have enough impact to lift their otherwise mediocre species above the king of the hill species. This can lead to situations, where species with the potential to become the new best species die out before ever getting the chance to reach their full potential. So, like I said: It works just like natural genetic evolution... A species doesn't automatically survive just because it is fitter. There also have to be the right set of random circumstances to allow them to succeed.
P.S.: One interesting experiment you can do with NEAT is to have to mutation rate ALSO me a trait that can be mutated. That leads to some low-mutation species that keep SLOWLY improving their positive traits and several high-mutation species that keep trying out random stuff. This stops a typical problem in machine learning: The algorithm settling in a "just-good-enough" plateau instead of keeping to improve in the hopes of finding an "even better" plateau further down the line.
@@LutzHerting this can be a video on its own. Or even a blog post series
@@LutzHerting 's also a interesting plan to use a shifting fitness function, or an array of 'em ^^
@beepbop that feels so much like how some gamers I watched approach the original Dark Souls.
They get taught the mechanics, receive a shield and never do anything besides blocking and hitting back. It works, you can play the whole game with that strategy.
But it is most of the time a very insufficient strategy.
one of the best things about these is when your AI finds out a trick to your programming and starts exploiting you. funny as hell
Is it exploiting or failure to limit parameters? I mean the Ai just does what you asked it to do, it has no concept of cheating or exploitation.
@@missionpupaexploiting.
@@missionpupaI mean the overwatch 2 AIs will walk through walls sometimes because they have found pixel wide gaps and can spam input movement commands every tick so they can just kinda clip through the walls then shoot you from under the map it’s not really a failure of parameters as much as a failure to block exploits
@@Grebogoborp wait what
@@NonsensicalSpudz flats has a video on it you should look it up it’s hilarious
This is honestly one of the best, if not the best Code Bullet video there is. It was an absolute blast to watch
My favourite is the Tetris video
Yeah so funny ong
This video totally reminds me of the days I’ve spent coding shitty little games back in my teens. I subbed for the nostalgia factor alone, I can relate to having a million bugs with no clue what I’m doing wrong. The trial and error is just a part of the fun!
I always love seeing timelapeses of bug fixing in videos where someone shows themselves coding - Being a java developer myself, I can truly appreciate that :P
Instead of fixing the ladder glitch in PPO algo Code Bullet punishing the AI for falling off is such a good parent move
Honestly, the whole part of debugging the gameplay and code was the most accurate representation of game development.
you're amazing dude, honestly your content is so relaxing to watch cause the ammount of work you have to put on, so we can just watch and relaxed like it was nothing,
MUM, CODE BULLET JUST DROPPED ANOTHER VIDEOOOO!!! woo
WHOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO OOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO OOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO OOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO OOOOOOOOOOOO OOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO OOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO OOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO
Correct spelling of mum 👍
@@hmm_-. anti lgbtq? Just asking bc your name
I thought you said "noo" lmao
@@Potatoking1 always and always
I actually really like how you explained everything!
Most of the time when a youtuber makes “AI plays X” or “AI learns to Y”
They don’t explain in more detail how they did it, or they skip over a lot of the crucial information when it comes to it.
Thanks for going the extra mile and actually going into things, even if only a little bit.
we love code bullet
Code Bullet actually shoots the relevant knowledge into your brain. Hence the name.
"So as to how this thing works, -- your guess is as good as mine, I have no f*cking idea but at least it works"
"skip over a lot of crucial information" that precisely describes his explanation. No critique towards him, explaining that shit takes ages and I understand why he doesn't do it (it would also be boring af), but he doesn't explain it well.
@@EvykhaitsSchmurf-tg7gehe doesn’t explain it well or in depth to every kind of code… he explains to us neruron activation monkeys in a way we will understand and at a level deep enough to explain some nugget of inform without boring us.
The chaotic energy in these videos just keeps growing and I'm absolutely on board.
One of your inputs should have been the rate of barrel spawn since it is something predictable by players after all. This way they would never die in the barrel spawn point. Great video by the way :)
Next time you want ChatGPT to explain something, ask it to explain it in the style of Code Bullet. I really want to see you react to it trying to imitate you. I checked, and it absolutely knows about you.
That's genius, I need to try it now
ChatGPT doesn't really know what it's talking about with games and stuff in general. It told me that Ghost type is super effective against Fairy type in Pokemon, which is just entirely wrong
Codebullet getting scared of something working properly was hilarious.
There's a certain irony in Code Bullet disliking an AI's explanation of AI techniques and preferring his own human explanation
The amount of effort that you have kept in a single video....
Dude honestly if you would have kept like more 10 sponsors i would have happily sat and watched all of them till the end
I don't think i can code a even 10% of what you did in a few months
Really amazing video man
Great work...
I like the balance between random entertainment and coding/AI a lot more in this video than the last. Always love the uploads!
I love the chaos of the process. It really gives you a sense of how many times it truly takes programmers to get stuff done 😂
As a person who has no idea how to code, I can say that your videos are very entertaining
My first time discovering your content! Mathematician and computer scientist here! This is so great! So much fun and hilarious! I really appreciate it, and I felt like I learned something that was a lot of fun! Definitely subscribing!
I love watching a successful programming channel that doesn't understand letters with hats on them either just like me! So quirky and relatable
The fact that he has the Honest Trailers epic voice guy read the AI explanation made it so much better.
Was that a cameo or some text to speech generator we should all be aware of? 😄
@@zorglub667 just what I was thinking.... HonestGPT
Took me a second to notice it was AI generated.
@@DanieleGiorgino but how? If there's an epic voice guy AI generator, I must know 😄
@@zorglub667 there are ais where you feed it a few minutes of voice and it can recreate it pretty well
Honestly... I love your editing style and your content. I continue to admire your effort and sacrifice!
Code Bullet always delivers!!!
Also for me, I loved the explanations and the glimpse behind the scenes.
I know if the video gets too technical viewer retention kind of takes a hit, but this time, I thought there was a healthy amount of "nerd-talk". Ty!
Finished making my first app with this in the background. Thank you, Code Bullet :)
I feel like I'm being spoiled with so much Code Bullet content in such a small span of time.
Your video editing gets better and better with time. I believe this one is the best so far for various reasons. Just want to say I recognize and appreciate your efforts. Well done.
The ✨animations✨
@@revimfadli4666 The animations were great, but it's other little things that have improved as well. The Dialogue, the tempo,, The video overall feels more cohesive while retaining all of the wonderful chaotic energy of previous vids.
NEAT is pretty neat... (*groan*) One problem with it is that it often throws away good solutions because the mutation can often be quite aggressive and throw out long-term positive traits for short-term gains. That said: This is literally how real-world genetic evolution works too. So for this algorithm, it pays #1 to have bigger population sizes, #2 to be careful about your mutation rate, and #3 to give it enough time to run. In all experiments I did with it, it often reaches a plateau where not much happens for many generations, but after a long time, it suddenly starts improving again. I'm pretty sure it has to do with the "species" system it uses: Often, one species is so good at what it does, that even "geniuses" in other species don't have enough impact to lift their otherwise mediocre species above the king of the hill species. This can lead to situations, where species with the potential to become the new best species die out before ever getting the chance to reach their full potential. So, like I said: It works just like natural genetic evolution... A species doesn't automatically survive just because it is fitter. There also have to be the right set of random circumstances to allow them to succeed.
P.S.: One interesting experiment you can do with NEAT is to have to mutation rate ALSO me a trait that can be mutated. That leads to some low-mutation species that keep SLOWLY improving their positive traits and several high-mutation species that keep trying out random stuff. This stops a typical problem in machine learning: The algorithm settling in a "just-good-enough" plateau instead of keeping to improve in the hopes of finding an "even better" plateau further down the line.
hamburger
It's nice to know that even simulated evolution suffers carcination.
hamburger
@@CalvinArt nft pfp lookin mf
you can implement speciation to fix the "aggressive" problem
2:59 I was playing Mario kart while watching this AND THE COUNTDOWN ALIGNED PERFECTLY WITH THE RACE THAT WAS STARTING
12:45 thank god for the car video, I lost interest 0.0000004 seconds into the timelapse and I really needed it to help with focus
22:05 That caught me off guard and now my face hurts from laughing
Hilarious 😂
I now see why it takes you so long to upload. Creating a bug every single time you add a new feature is a genuine gift. Never change
Music in between methods like NEAT, PPO is epic. Love your videos.
I love the extremely 2020’s approach of using raycasting for floor detection. The original Donkey Kong programmer would have lost their mind. 😂
I too lost my mind for a bit
@@WingMaster562 same tbh, I was just sitting here thinking "Wouldn't just a simple AABB collision algorithm be better?" but hey, he makes games on youtube for a living so he probably knows whats best
@@MythicTF2 trust him, he doesn't
@@treeck3724 such an unwieldy way to code, it's fun to watch though
What’s wrong with Ray casting?
I loved that you went more in depth this time! I can imagine a lot of us here watch and enjoy your videos because we're programmers ourselves, so getting more details is always interesting (in my opinion). Loved the video!
I too feel that excitement when testing basic movements. People got no idea how tedious it is to implement those perfectly…
As someone who who had to make a platformer from scratch in Java I understand how hard the first part was
24:15 There's a sentiment I can get behind! Instead of fixing the bugs, teach the AI to avoid them at all costs! Lol, this was an interesting video, thanks for comparing the three, I liked how you mentioned the strengths and weaknesses of them and how it's more like a "pick the best tool for the job" than it is "this one is the best".
Code bullet: *becomes game dev*
Playerbase: *finds bug in game*
Code bullet: “Where’s my ban hammer?”
E
Instead of paying money to fix the hole in the floor teach the baby not to fall in it
(23:00) You should preferably also set the distance to the nearest ladder upwards and nearest ladder downwards. Since you can add a lot of inputs, the nearest ladder upward can also have the inputs for the next barrel to that ladder that might fall down it.
I like to imagine the time between episodes is actually spent making more poses for codebullet's vtuber sona, and he hammers this code out like a legend over the course of an afternoon.
Life: gravity pushes you against the surface below you
Code: gravity shuts off if you're touching the ground
This man has the most elite upload schedule 😂
it took me the same time it took him to upload 15 of his videos (provided he doesn't upload for two months... which is guaranteed) to get a cs deegree
@@thomask2133 provided you actually get the degree 😏
21:30 "As soon as some letter start wearing little hats..."
The funniest part about that is that it is called a hat. The A is A hat. At least in stats and I assume tin this context as well.
3 AIs competing was really interesting. It laid out a lot of pros and cons of each while showing actual results. Nice 👍
thank you for all the technical stuff, its by far the most interesting part about the vids
didnt know one of the ai methods youd often see on youtube is no brain at all but just a stupid list of instructions
also had heard of the different methods of generating offspring / reward and punishment, but didnt know they were two unique approaches till now
if you do this next it might be interesting for you to simulate what the ai sees/knows
Real
Completely forgot you were planning to make an ai. It was so intriguing to watch you just rebuild the game. 2 awesome subjects in one video
it's hard to describe the fear of something working the first time when you know it SHOULDN'T HAVE WORKED THE FIRST TIME
After talking to people that work with AI, one of the things they mostly agree on is that not even they have any idea what is going on in the back end.
What IS going on in the back end?
That question is harder to answer than physics probably
@@Hypernova7777Look up how neural networks function, it’s not actually very complicated on paper. The issue is that with enough nodes, it becomes impossible for humans to possibly follow exactly what’s happening in the “brain” of the AI.
@@IAmUnderscore That's what I meant...
I know the base stuff about nodes.
@@Hypernova7777 Ooookkayyy….
@@IAmUnderscore I took a class on this
0:36 so it needs the code bullet treatment
20:00 Not only has the algorithm deemed Jumping Unnecessary, it's also stopped paying attention to where ladders are (opting instead to just keep moving along the platform until it stumbles onto one), and to how the barrels are moving, (opting to just move as far away from the closest barrel that it can). This second part is probably why they kept hanging out behind Donkey Kong - they move past him because he has no collision, and then he spawns a barrel, at which point the AI goes "I'm not going anywhere near that, stick to the far wall".
You could probably have convinced them to start jumping if you'd kept the point score for jumping over barrels and added that as a secondary condition of some kind, but that would probably have resulted in some of them just point-farming barrel jumps instead of completing the level, and would have taken more effort to add in and bugfix; plus, this way it works as an excellent example of how the algorithm can produce unexpected behaviour, so it's for the best.
to get the dots to not get stuck in the floor like what happened at 1:24, you can split the movement into 4 sections per frame, so it moves 4 times per frame instead of one per frame. it will move past the first quarter, then the second one, but if it hits something in the third quarter, it will go back to the second quarter and stay there.
i learned this from mario 64, increasing the step size from 4 to 16 or something will make it smoother
I thought the point of that was that if any quarter step hits something, it goes all the way back to the first.
I think that you need to add a zone that will eventually rise from the bottom, and you need to divide it into levels, and if the AI touches the highest level, then one point will be taken from it, if it touches the level below two points will be taken away from it, etc. This provokes the AI to climb faster rather than stay still.
I made a really crude, crappy AI that learned Super Mario Bros (the first level...) and it helped to reward them for moving, penalize for stopping too long, and immediately kill if they don't move within the first second.
I appreciate your recognizing the last video. I thought for a moment that I somehow missed it, but then you reminded me that I just left partway through. Yeah, that was a mistake. Glad you're back, and glad to hear about another channel!
13:33 The AI finding a glitch and taking advantage of it is freaking awesome 🤣
Even spiffing brit isn't safe from ai
@@Alucard-gt1zf The Genetic Algorithm is a perfectly balanced game with no exploits
I really liked that there were more explanations in this video; I find this stuff super interesting. Another great video as usual!
Awesome video! Your combination of code and tons of humor cracks me up.
As for your AI?
I will only say the following:
Still less cheating involved than Billy Mitchell's runs.
(And still a better love story than Twilight.)
Careful, you might get a lawsuit
@@MaximNightFury Would love to help him towards his next loss ;)
This guy narrates like a tenured professor and I am all for it
1:50 "I'm scared"
Man I relate so much, that's so true.
The worst in programming is not "It doesn't work and I don't know why", it's "It WORKS and I don't know why!"
At 9:39, CB states "2 extra nipples" while adding 2 nipples to a nipple-less entity, presumably a human. However, we are aware that all humans have 2 nipples by default. Therefore, we can conclude that CB canonically has 0 nipples.
18:22 where's our car??????????? my gen z brain cant function without gtav gameplay covering half of the screen D:
The 'hat'above letters is used in physics to show its a vector, or a directional thingy
I loved the way you explained on how to apply the different AI in a easy to grasp manner. Would love a video were you would go more in dept on your code! Thanks as always for the amazing video :)
i love even coding experts go through a ton of challenges when it comes to coding. also the thing of just “moving a red square across the screen”. like bro, that’s a big step when it comes to coding😂. like all u have to do now is get a character and then change it from the square to ur character of choice and then now u have a person that moves instead of a square
One of the issues I thought of immediately is that sometimes dodging barrels requires moving backwards, and because of the way you designed the PPO it'd never do that.
That being said, three AIs, one video, I am very pleased.
@21:29 Yes, the small hats are definitely a sign of trouble. Actually a lot of people seem to be noticing this these days.
You are a legend of a coder, you inspired me to make an AI bot of my own and I appreciate what you do for our society. Keep up the work Code Bullet, I like you.
Man that driving at 12:40 was sick, full screen next time pls
Ya it was
You really do seem to be the only person making content like this. It's great
Classic Code Bullet:
“Can it go right?”
*block moves right*
“Can it go left?”
*block moves right*
“Close enough!”