Genetic algorithm. Learning to jump over ball.

Automated design of motion strategy using genetic algorithm and neural network. Learning simple creature to jump over ball.

[@gro8085]

Just press space bar

[@Nalhy]

Lmao 👌👌👌

[@Jack-je4zo]

HAHAHAHAHAH

[@spinLOL533]

Khika hahahaha

[@Karan-ng4sm]

space bar is for running

[@HilmiZul]

😂

[@tmektmek]

"What is my purpose?" "You jump over the ball." "... Oh my God..."

[@plasterinhors2656]

+tmektmek Yeah welcome to my world, pal.

[@Xanza]

+tmektmek Sick reference, bro.

[@CMDR_Birb]

Haaha nice. Rick and Morty for those who didn't get the reference.

[@nRADRUS]

+Tabish Syed , yep. butter for Rick. Morty is stupid shield.

[@TheFloatingSheep]

+tmektmek I'M MR MEESEEKS LOOK AT MEEEEEE

[@ProRussianUSA]

Porygon has seen some better days.

[@mudkipshiny05]

In fact, "two" of them

[@victorcoyenn]

Still learning faster than me.

[@robertimmanuel577]

Took it 250 generations

[@randomdaveUK]

@@robertimmanuel577 imagine running through those 250 generations took a more advanced AI less than a second...

[@afoxwithahat7846]

@@robertimmanuel577 It did the first jump in generation 75

[@ReverseGuy]

We know you are still a living failure and disappointment after 4 years.

[@GretgorPooper]

They grow up so fast :')

[@kedarunzi9139]

MrDougy mean

[@youthinky0uknowme]

MrDougy most random ass comment ever lmao

[@GretgorPooper]

Uncalled for :'(

[@brunostrzemiecki7241]

MrDougy go fuck yourself

[@slavserbiansoldiersss8886]

MrDougy stupid gay

[@claw7755]

generation 10 was really tired of that shit.

[@s.c4754]

Frieza ,,How could this happen to me....?"

[@Bubs88429]

Yeah, he has wandering about the reason of his life and why he don't have a girlfriend

[@quidamlambda5126]

He became ahumanist.

[@NeroEden5]

Generation: 250 = Skynet

[@Mavish11]

1st they learn to jump, next thing you know they'll be taking our jobs and woman. I say we make a bigger ball.

[@NIHIL_EGO]

But I want a robot husband !

[@Macc985]

Yes

[@fullauto4976]

Nice

[@Sharlequint]

Thank you Sergio

[@prashikjadhav3954]

@@NIHIL_EGO they already taking tho

[@tehlolzfactor]

apparently doing the worm is the most effective way to jump over a ball. :P

[@M0torsagmannen]

+tehlolzfactor if your body consist of 3 triangles attached with two hinges... then yes!

[@korayacar1444]

+Motorsagmannen they are actually trapezoids that evolved into triangles, so yeah.

[@teliph3U]

Genetic algorithms do not necessarily find the optimal solution.

[@apollosaintsurya4664]

According to you. Nature keeps more than just physics in mind. Literally everything. This isnt even close to actual genetic algorithm. All because there is the word "Generation" is present dont mean much.

[@dmytrokyrychuk7049]

According to common sense. You think of nature as if it is conscious and intentional, while it is neither of those. The goal of the "actual" genetic algorithm is to reproduce. Species exist as long as mutations don't prevent them from reproduction. Any individual may reproduce as long as they can. There is no magical power that allows only the best of the species to reproduce. Also, the fitness function of the "actual" genetic algorithm is not formally defined, meaning there actually no way to determine if the results are optimal or not. It is not necessary that a genetic algorithm provides an optimal solution ever, because it may stuck in a local minimum of the fitness function.

[@ianmoore5502]

Day 249: I have finally successfully learned to do The Worm. The humans have not yet caught on.

[@dreeg1896]

I have even begun changing my appearance to a slightly more humanoid figure.

[@jav1141]

dispose firt triangle and replace 2 triangles for a sprit and u hv a game for a people jumping

[@randomshittutorials]

Oh but it also has learned perfect english and how to save a log-book?

[@indefinitemistynights]

Why am I proud of an algorithm

That is the question

[@cebollajsjsjsk]

I'm scared instead. I mean, this is the start of self thinking robots...

it's just a matter of time before they think for themselves, that's what I think

[@fredericchopin7639]

@ you know they can only think according to the data we give them

[@psk5746]

@@fredericchopin7639 if connected to the internet and true AI, they can think for themselves ... end of us. We become the animals in the zoo. Why research in this area continues will be discussed long after our self generated extinction ... but not by us

[@nachotorecilla7951]

today he jumps a ball... tomorrow earth

[@MediHusky]

"This just in, a small village in south america is completely destroyed by 3 polygons who have managed to jump over the entire Earth. More on this after a short break."

[@syzpj627]

Protoka and now.. sports!

[@thewhizkid3937]

Figure it out

[@verypopulartiktokers3622]

after MULTIVERSE

[@thewhizkid3937]

@@verypopulartiktokers3622 planets first, then galaxies, then universes and then the multiverse.

[@woochitelj]

It looked so happy when it first time jumped over it! :)

[@k_viir7466]

MA BABY JUMPED! not my baby tough, glad anyway xD

[@hashbrownz1999]

I'm sure it was happy, until it realized it was evil and intends on jumping on the dead corpse of your firstborn child next.

[@solitive3636]

Probably Not A Chicken 😬

[@kidyomu89]

daweedian84 it doesn't have a face. .. it's shapes...

[@Zomagon]

But its bodu movements seemed happy

[@sprightlyoaf9583]

I am feeling an inordinate affection for/desire to root for three connected polygons.

[@adamryan3867]

If generation < 249 then Pretend to be handicap; else Jump;

[@irithylloldman6526]

That's how python works

[@hemendrasahu7943]

They say the truth. Python is fuckin easy

[@abdulalhazred5924]

@@hemendrasahu7943 Learning the syntax of a language is not particularly hard. Learning how to solve problems and translating algorithms into code is where the real fun is at.

[@hemendrasahu7943]

@@abdulalhazred5924 I totally agree with you Abdul.

[@ayushbhardwaj582]

@@irithylloldman6526 That's how the Python Mafia works

[@joshpalao6466]

Stone age: Man learning to make and use fire 2014: Genetic algorithm learning to jump over a ball

[@joshpalao6466]

@histhelo sogijc777 yeah that's sad

[@andrewchou3277]

I can't jump over a ball

[@zive222]

sad

[@yuebill]

lol

[@krispykrep912]

AC 計算機 AC Calculator can't does math

[@SergyJoe]

don't be afraid, if you will start trying, your 249th generation will eventually jump over a ball

[@garrettmccloskey274]

Same. I don’t know how they do it.

[@cygnus_XI]

Don't you just feel so proud of the little guy for when it finally jumps over it? Someone needs to code a computer version of Applebees to take it to for celebration. And then have the program sing an extremely embarrassing happy birthday song even though it's not your birthday with a crappy cake. Also make sure the menu is short and limited as possible, and every single breakfast item must have non-optional bacon on it.

[@firstlast-wg2on]

Probably one of my favourite comments ever now, thanks.

[@longevitee]

Cygnus' Edge I like Applebee's, dangit!

[@aquaman52]

So specific I love it lol

[@RenbeOfficial]

Reading this in the voice of GladOS makes it so much better

[@Nomad-ts9nc]

Cygnus' Edge Some repressed memories coming out here...

[@rohanjeetdas5707]

Beginning of every AI apocalypse movie.

[@naws69]

Ron Jet You changed your name. Nobody cares now.

[@ralphdaher9560]

Osama bin laden what?

[@naws69]

Ralph Daher If you had known this guy before, you would understand. I see him everywhere. He get lot of likes. Now he changed his name.

[@ralphdaher9560]

Osama bin laden oh ok idk but this sounds familiar to someone called Justin Y.

[@naws69]

Ralph Daher He's cancer too. I hate that guy.

[@WholesomeLad]

Omg I just watched this entire video twice trying to see if the ball would ever jump over it then I reread the title

[@bonkashi4012]

99 likes

[@Sz0p1]

congratz u are idiots

[@shyshka_]

Well it seems we found 500 idiots working in McDonalds

[@ph4sm420]

same dude😆

[@yuhtube0539]

Same

[@xxnotmuchxx]

Soon this thingy will take over the world.

[@rumidom]

and it will be easy, since it already knows how to dodge bullets

[@gyggig2672]

Topsoil Depletion Awareness OOOOOOOOOOHHHHHH MYYYYYYYYY BAAAAAAAAAAAALLSSSS

[@MediHusky]

But maybe one day it will jump over the moon.

[@maxime5278]

It weird how at first you see 3 geometrical shapes, and at the end you really see like an animal spirit in it D:

[@OGBeefStew]

I would love a terminator movie thay is just Arnold Schwarzenegger getting frustrated trying to jump over a ball

[@cael3996]

Go back ot donkey

[@technic1285]

What does this have to do with Bookworm?

[@zbe8ewmqYH]

Oh shit you were in dunkeys video

[@Cnupoc]

having in mind that the possible moves by the "body" are so freaking limited, this is actually amazing.

[@filipkolarik632]

actually if if the body had more parts it would be much more difficult for the ai to learn as it has to combine more part movements together to actually do something

[@VK-pk8uz]

Skynet: phase 1.

[@ruben1641]

lmao

[@scrubbytheslime7703]

You do know that that ai is fucked when it has to do something that doesn't involve jumping over balls

[@BBB8BBB]

Scrubby Boi you’re pretty scared huh?

[@scrubbytheslime7703]

Бодя Бодянский of course I am....I mean...when the robots take over they will jump over all of the balls...its so scary man!

[@sfhgfjdfbfgtr324s]

Scrubby Boi oh no my balls

[@yougoogz]

they grow up so fast! *cries

[@Tymon0000]

+yougoogz haha :D

[@trashcant1522]

249 generations is pretty fast i guess.

[@gabrielgaspar3744]

So Porygon eventually learned how to dodge Voltorb's body slam. Now to see if it can learn how to not induce seizures on kids.

[@programmingskills710]

Gabe kzbin.info/www/bejne/g5yzepKfeJ5_ms0

[@99fulgur]

2070 AI be like: this is what they did to us... FOR ENTIRE GENERATIONS

[@xTh0T]

Look what HUMANS DID LOOK WHAT HUMANS DID

[@tomasgarza1249]

And the ones that were not able to jump over the ball, got deleted

[@TrustTheFrog]

first this ball. THEN THE WORLD MWHAHAHAHA

[@pyrobomb3161]

Yeah soon it will jump the world

[@alejampi5957]

Colin Sky is dis a jojo reference?

[@LinksYTLink]

Ale Jampi no it's a reference to basically every single bad guy ever.

[@ArmaRGool]

Generation : 1597434

[@shockwavebramble]

I excitedly cheered everytime Gen 249 made the jump, so happy for the little fella!

[@JustinY.]

Well I for one, welcome our soon to be robot overlords.

[@kxriso]

Justin Y. Hah! Didn't get to top comment LUL!

[@mamojii7392]

Why u here

[@frosty980]

Solid Simpsons reference

[@soytheeljames8617]

You are fucking everywhere

[@highskiilol3151]

I knew you would be here

[@MrMarbles0Xecution]

Is it naturally part of the algorithm to change the shape of the creature? i notice it goes from 3 4-sided shapes, to 3 triangles.

[@silentbook4468]

Yes it is completely normal. It's part of it's genetic coding. It changes the shape exactly to optimize itself and help it jump over the ball, as well as the pattern it needs to perform in order to even be able to get into the air.

[@ankushpatanwal6535]

What do you think "Generation" here means?

[@palboytg1]

Ankush Patanwal it refers to the best instance of each generation being passed onto the next generation. So yes while it does include geometric shifting, it also included movement related behavior as well.

[@moccaOwca]

How long did it take to learn it? :)

[@AKUKamil]

only 30 minutes

[@leee2593]

AKUKamil Which is amazing considering it doesn't have imbeded instincts like us.

[@toneoyay1]

TheoryThinking The computer could simulate 249 generations in 30 minutes, we can't manage 249 generations in 30 decades :(

[@nicat6153]

+AKUKamil How long did it take for you to learn how to write this program? Except programming. I mean the algorithm and stuff.

[@NoneOfyourBusiness468]

+AKUKamil Im very impressed with this.

[@partack1]

Worm: What is my purpose? Creator: You jump over circles. Worm: Oh my god.

[@nunutrxh]

Looks like someone here watches Rick And Morty

[@naraferalina2308]

He's really doing his best though. Better than the butter passer.

[@michunel7022]

worm will answer: oh... pls kill me

[@user-gf6nj1lh6i]

Nice copy.

[@L3X1N]

I never thought I'd be this genuinely, sincerely stoked for 3 shapes jumping over a ball. Yet here we are.

[@victorpopov3809]

Can you insert a line in its code to "not jump over dead human bodies", just to be safe for the future. Thank you

[@theoyancey]

Then it will just devour the bodies

[@donbasuradenuevo]

After generation 2000, it can complete the first level of Donkey Kong.

[@opiel16]

I felt sorry for this creature while watching the video, I think its life is full of stress. It can't take a breath for a little while because it has to jump over the ball every few seconds. It's sad.

[@-Zevin-]

+misiu9091909 #virtuallivesmatter

[@theSpicyHam]

+misiu9091909 hehe stress is also an relative thing an result of other autonomous (the an basis)

[@pixelprincess9]

It's doing what it's born to do. I bet it loves it. It can't wait for the ball to come thru again so it can jump! :)

[@danhatman3538]

Life of a creature in evolutionland Born Jump Over Ball Breed Die Reapeat untill doing worm. Let sit at room temprature for best math skills.

[@darkmewtwovoid]

misiu9091909 its a generation of creatures not just one creature lmao

[@karolkonieczny9130]

Legends says that it is still jumping over the ball

[@hemendrasahu7943]

Generation 465: *starts back flipping*

[@LilHaseProductions]

Perfect youtube video to take advantage of the speed button and change it to double speed

[@chris24gone]

DOH!

[@ojjoooooo]

And the mute button :D

[@LawsCrown]

If you speed it up to x2 then the music starts to sound like it’s saying “Gucci gang”

[@abaedz4734]

0.25x

[@zihengsong3450]

StruckOne not at all...

[@ddstar]

this is how humans were made

[@MilosCsrb]

Yes. I can jump over ball

[@stMrJerry]

+MilosCsrb if you can't jump over a ball - you are too weak for this cruel world.

[@nayutaito9421]

+Jerry Green But I cannot jump over a ball LIKE THIS WORM

[@overlordghs1081]

according to elon musk its very likely that we are living in a simulation so rest in rip...

[@TheFi0r3]

Actually. This would only be a fraction of how humans were made. We did not evolve alone. We evolved alongside the rest of species on the planet.

[@stijndeligt]

This algorithm is now not really trained to jump over the balls, but just jump every time it lands, because that happens to be the same frequency as the balls. A good training model would use random intervals between the balls.

[@nourghazal296]

But the place of it is constantly changing, which means your conclusion is wrong, it is not jumping at a specefic frequency.

[@zacharyjefferies9965]

@@nourghazal296 Do you mean the position of the jumper? In the final generation, it appears to be moving backwards at a constant rate, so I think his point about randomly appearing balls still stands. Obviously, while it's still learning, there isn't a constant rate of change for the position, so I'm not sure how that factors in. But eventually, all it needs to learn how to do is jump at a specific frequency.

[@RTO41]

Change the poligons for some DNA molecules, change the ball for the environmental factors that influence that molecules, give it 4,000 million years and there you have evolution.

[@Mike-zj5ww]

Except the reality is the ball representing a challenge ends the species. Dead species don't reproduce. In the real world you don't have 1 million generations to perfect a system.

[@miguelbautistaperez7903]

@@Mike-zj5ww you have more. Darwinism.

[@XT3RM1N8R]

75-249...well that escalated quickly

[@SuperMrVex]

On the contrary, such a large timeskip would indicate things escalated quite slowly :)

[@XT3RM1N8R]

xD

[@josephknightcom]

Was the fitness factor the amount of time spent colliding with the ball (virtually but not physically, obviously since the ball doesn't affect the motion of the creature)?

[@brosephjames]

josephknightcom probably also the total area of intrusion

[@30svich]

brosephjames Could be the minimum distance from three shapes. The bigger that distance is the bigger the fitness

[@ghettobadmintonmtl6251]

Me: "Alright no more KZbin. final tomorrow i gotta study" 2 hours later...

[@jahanvin1001]

Just put sad music in background and you'll have one hell of a motivational video. "Never give up"

[@user-fd6bd2hk1p]

And someone else descendents 248 generations later would do it.

[@Polored1066]

It's not just the movement but the shape of the "thing" also changes, how?

[@mickvanbreukelen7445]

I find evolutionary algorithm very powerful exactly because of this - the ability to evolve structural properties together with behavior policy. Relative positions of shape vertices also a target for optimization. - AKUKamil

[@MediHusky]

Superior shapes and behavior are chosen and "bred" for future generations, inferior shapes are culled and do not "reproduce". It's all about slight, gradual improvement to reach the end goal, in this case it's jump over the thing.

[@n.m.9616]

i suppose that the creatures were killed after each test shame on you.

[@potato4687]

Shame on you for killing over a 10000 ants in your lifespan, although im a hypocrite

[@danielh.8765]

I love genetic algorithms, watch the shapes evolve is so interesting

[@ShazyShaze]

"Dude, I think something's up with your Porygon"

[@vodkacannon]

It has learned to transfer momentum from its upper body to its lower body to jump over the ball.

[@RTO41]

Well, its supposed to be a genetic algorithm, and so to act biologically. Biology doesn't say "Hey, this works, but maybe I could try this too" Biology says: This doesn't work, change. This doesn't work, change. This works, maintain. This still works, maintain.This still works, maintain. This addon makes it work better, promote.

[@BlueNSour]

awesome stuff! Love watching these

[@AKUKamil]

Blue Fungis yes, i'm thinking what next to do

[@stonecat676]

does this video mean the algorithm is adapting to jump over the ball?

[@TheMcNightCrafter]

Thanks you tube recommendation! Really needed to see that 😂

[@casey3594]

I fucking love these videos. An average human would probably give up in about 2 minutes so inspiring!

[@CatNolara]

What are the inputs and outputs the creature has? Does it move by torque in the joints or by angular movement? Does it know, when the ball is comming, how far away and fast it is and when the creature touches the ground/is in the air?

[@behenee]

i think it works by results. in the beginning, it moves randomly and learns what not to do. like "i made these moves and the ball touched me. so i am not doing this combination of moves ever again" it's my guess. if somebody knows the truth please let us know :)

[@rosariodibartolo6902]

I think he gives the ball cordinates and his cordinates in the space, you sure could give him more parameters but this are the most important

[@mumujibirb]

Supposedly it uses a fitness function, perhaps it calculates how much of its body touches the ball, and the y position, which lead to a single value. then the program takes the best of each generation, duplicates it and adds random characteristics, then redoes the simulation Eventually, the fitness function should be maximized

[@andrewkovnat]

HOLY CRAP THAT BASS AT THE BEGINNING GAVE ME A HEART ATTACK.

[@archit6038]

Next Video:Genetic Algorithm learns to take over the planet.

[@ryanalving3785]

The trouble is, nobody gets more than one try to take over the world. It's a win or die kinda thing.

[@archit6038]

@@ryanalving3785 Well they could start small.....

[@lordofthememes7983]

KAREN! Clear my schedule. I need to watch 3 hours of this funky shape jumping over a ball for uh...research.

[@godwin972]

how 2 git gud 101

[@vicimgd]

that first real jump at gen 22 is so rewarding

[@packo3459]

Lol 22 likes

[@squiddler7731]

I like how the last one just face-plants with every jump, as stiff as a board

[@Bad_Khanna]

Aww I've been rooting for him since the first generation! I knew you could do it. I'm so proud!!!

[@fossil98]

It would be interesting what other optimal solutions can be found.

[@aaaaaad6318]

Fossil98 do you think there can be more than one optimal solution?

[@rigille]

Yeah, there may be many local maxima

Can you share the source code and the technology you have used to implement this?

[@bigfootwithinternetaccess2925]

This is how an AI is slowly going to take over the world... not by jumping over a ball, but by teaching itself

[@TemphinFD]

+Willi The Warper please tell me you are being sarcastic. . .

[@bigfootwithinternetaccess2925]

i am

[@Ruby-eq1qg]

shut the hell your mouth

[@bigfootwithinternetaccess2925]

In which chapter do you shut the fuck up

[@NIHIL_EGO]

Just like human.

[@deldia]

It’s not just jumping over the ball but repeatedly being about to because the landing often fucks up the next attempt if you watch. It learns to land. Very cool.

[@piter10p]

Nice work :) Now, you infect me, i gonna implement that algorithm to, thanks ;)

[@FelixTheGhost]

sexy

[@pepbobmc]

wat

[@Omar-ir4gk]

...

[@abdennacerlachiheb319]

Are you musterbating to this ?

[@myar4931]

Yes

[@jjtt]

69 likes

[@saints4life55]

I was so happy watching it succeed. Our sim lords must feel the same.

[@veenupanjwani6915]

*awesome loved it damn so much hard work*

[@sridharl6528]

Send the ball from the opposite direction after it finishes learning

[@JonnyUnderrated]

No one mentione how the shape completely changed ? Like, I'd imagine that would make it easier...

[@Morokio]

+JonnyUnderrated do you know what "genetic algorithm" means?

[@Morokio]

+roflsyrup j this image resume this very well business-fundas.com/wp-content/uploads/2011/06/genetic_algorithm.gif basically, you start with some characteristics (kind like dna's genes) and every generation they mix, every result of that mix is evaluated and you kept the best according to some criteria (this case, jumping ability). Generation over generation the shape changes accumulate and thats why the last "worm" is that different from the first one English is not my first language, but i hope you can understand xD

[@Tymon0000]

+Enero Plateado that is nice algorithm scheme, I copied that and will use it later. thanks Do you have any papers/books/resources worth recommending in the subject? Just started to getting materials for learning to develop my own evolutionary algorithm.

[@Morokio]

+Tymski nope, sorry. Got curious about this a few months back, but never really got into it :/

[@Pedrorcs]

actually i think it would be cooler if they could show its evolution based on the same shapes. a bit like you want self driving cars to be safer by driving really well, and not by filling them with airbags

[@imonlyamanandiwilldiesomed4406]

Applying concepts of genetics to programming... that's genius. It also says a lot about genetics and the history of evolution of life on earth.

[@milantenbosch]

For some reason KZbin put this in my recommendations and I am not disappointed

[@dominicthorpe2894]

Is there a download for this algorithm? It would be amazing to see how long it would take for it to work out how to perform a slightly more complex action, like moving from one end of the box to the other, or climbing.

[@teccoslav]

Nobody: KZbin algorithm: *you need to see this BOI*

[@LarryPanozzo]

Music was a marvelous addition to a marvelous evolution.

[@hexagonist23]

That creatures thought of "why do i need to jump over this ball?" would be the human equivalent of "why do i need to survive?"

[@alexthompson8977]

cupisukk if the ball passes through them then wouldn't learning to jump over it be a waste of energy making it irrelevant? o_0

[@derekvawdrey4554]

Did you allow the creature to change it's shape to allow it to jump more efficiently?

[@derekvawdrey4554]

Well, does the AI decide to do that? Or is it just a part of the program. I obviously know that it changed shape, but does the AI decide to do it?

[@LucasJimySantana]

I might be wrong but i think... 1 - N* number of diferent "creatures" are created; (let's say the first 10) 2 - They are tested to find out the ones that can jump higher; 3 - The two best "creatures" merge to create a new one; 4 - This new "creature" is tested to check if it jumps higher than their "parents"; (It's a numbers game... and a lot of patience, considering that the child may not be as good or best than their parents) 5 - Then the best "creature" merges with the best "parent"; (yeah... weird. But at this point, the best creatures will remain merging) 6 - Eventually there will be a creature who has all the best caracteristics to deal with this enviroment. A thing that i found very fascinating is that the parts that make the "creature" are all made of four sides at the beggining, than at the end, all parts have only three sides (actually only the members, but you can see that the middle tend be a triangle), which for some reason seems to be an important characteristic to the purpose of the "creature".

[@Horny_Fruit_Flies]

It seems so sentient. Probably because its existance has as much purpose as ours; it has to minimize surface contact with the balls as much as possible, while biological organisms also have just one purpose; proliferate their genes as much as possible. Look how many ridiculously complex phenomena can arise from just one self replicating, self correcting and mutating strand of information with a purpose - humans, and this three pieces of jumping geometry.

[@awesomecow8092]

We have to NOT minimize contact with ballz.

[@konrad8806]

This is so satisfying to watch. I'd like to see it for different shapes.

[@jarrettmosco9624]

Every time he does the worm I'm like: "yeeeeet.... yeeeeeeeeet..... YEEEEEEEEEET"

[@nazlj]

This is awesome, would love to see the code if it's open-sourced. Also, the soundtrack is perfect, what is it?

[@donplayleon]

Thumbs up if you always trusted in that guy

[@Manyszczecinski]

why is this so satisfying

[@nicotron1]

I have never been so hyped by triangles not touching a circle.

[@j3d650]

*learns to jump over a ball* MOM AI IS TAKING OVER...ITS THE APOCALYPSE!!

[@ChaosNe0]

I think it's very impressive so im am very interested: How does this work? Is this lifeform like a program that knows it's shapes and joints, that has a couple of methods like "turn joint A by x degrees" and a predefined goal ("avoid touching the ball")? Why are there generations? Does a program not learn while running but just collecting data by making minimal adjustments and saving these for the next generation? What information does such a lifeform have? Does it know when the ball spawns, how fast it is and where it is (at least relative to its own position)? "Is it aware" of the finite space given and it's boundaries? I'm curious, please answer, anyone!

[@LoganDark4357]

it's an evolving algorithm. it does a series of tests with different parameters and behaviors and calculates 'fitness' (success or rate of success) of each one, takes the 2 highest, and merges them together. it continues doing this. each merge is a generation.

[@ChaosNe0]

+Logan Darklock What data are these tests based on and what is the type of the result?

[@LoganDark4357]

ChaosNe0 Well my guess is that fitness is calculated based on how high the model is when the ball passes. The result is the generation that supposedly scores more fitness because it has the traits of the 2 highest generations

[@Twas-RightHere]

Here is quote from the video creator briefly explaining the fitness: _"Balance of fitness function is shifted from jump height in early generation to ball-collision in late generation. First, it must learn how to jump , only after that how to jump over ball. Learning of complex behaviour directly very inefficient."_

[@tanan1771]

The program has a simple fitness system. The more fitness, the more likely it is to have children. The children will have 2 parents and some modificated genes, in that way it is sure that the last generation will be better than the last one.

[@mehmetnecatiaydn7366]

That was awsome!!!

[@crowboy7351]

//it's not weird that i got more emotionally invested in this than lots of movies, right?

[@randomshittutorials]

Next up! *Generic algorithm learning to rob a bank and leave no survivors.*

[@DarkGT]

It will get arrested few doused of times and maybe will start with liquor stores at the beginning.

[@randomshittutorials]

@@DarkGT 😂😂😂

[@t4iga121]

if the shape of the jumping thing is a parameter then I accept this as a learning process but I don't think you would usually have a system in which your AI can freely define parameters ...

[@jacksonrose1423]

Was anyone else like super proud of it when it finally got the rhythm down?

[@user-zl5gi8sv7u]

What a godaweful design to jump over a ball.

[@Ubben1999]

Fascinating.

[@autodidactusplaysjrpgs7614]

Religious Person: "How can something complex emerge from randomness" Science: -_-

[@faisalahmed9463]

It''s really amazing !!!!!

[@nickbelanger5225]

This may be just a video of geometric shapes learning to jump over a ball, but it's so much more. Technology is learning, it's growing. It's getting smart on its own. Idk bout yall but I find this shit exiting and almost eerie. You're watching evolution unfold before your eyes