AI vs. AI in 100m Dash (deep reinforcement learning)

AI Competes in a 100m Dash!
In this video 5 AI Warehouse agents compete to learn how to run 100m the fastest. The AI were trained using Deep Reinforcement Learning, a method of Machine Learning which involves rewarding the agent for doing something correctly, and punishing it for doing anything incorrectly. Each agent's actions are controlled by a Neural Network that's updated after each attempt in order to try to give the agents more rewards and less punishments over time. Check the pinned comment for more information on how the AI was trained!
Current Subscribers: 264,870

[@aiwarehouse]

It took me months to make this video and it took my computer over 3 days straight to train/record the agents, I hope you enjoy it:D After teaching Albert to walk in the previous video, I read a lot of comments asking about what would happen if I used a more human way of punishing and rewarding Albert, so that’s what this video is about! Each agent starts off the same, the only difference being the design of their body. They’re each rewarded for moving forward and punished based on the efficiency of their movements (based on a muscle fatigue system), so by the end of the video they each should discover a movement that works efficiently for the body they were given. NOTE: Don’t worry, Albert is coming back in the next video, he’s hard at work right now improving his walk:) If you're interested in training your own AI like Albert but don't know how, there's now a really easy way to do it! Luda, an AI lab, recently built a web app that allows you to create and train your own AI using deep reinforcement learning (just like Albert) completely for free in your browser! You build your own character (called a Mel) with lego-like building blocks then watch it train in real-time on their website in just a few minutes (really). It's an awesome project, and just like my videos, makes deep reinforcement learning so much more accessible, which is why I love it so much. This section of the comment is sponsored by Luda, but these words are entirely my own, it's an amazing project that I would have been obsessed with had they released it before I built Albert. I've genuinely been looking for a sandbox/game exactly like this since I was a kid. They're still early, but they're giving my audience first access to their closed, pre-alpha build. Make sure you check out their site and create an AI agent for yourself!:D prealpha.mels.ai Now, back to our agents, If you want to learn more about how the agents actually work, you can read the rest of this very long comment I wrote explaining exactly how I trained them! (and please let the video play in the background while reading so KZbin will show the project to more people) THE BASICS Although it seems like there are only 5 agents training here, there are actually 40 copies of the video being simulated simultaneously behind the camera in order to speed up the training, so although the video makes it seem as though there are 1638 attempts, there are actually around 65k. Each agent is controlled entirely by an artificial brain called a neural network. Their brains have 5 layers, the first layer consists of the inputs (the information they’re given before taking action, like their limb positions and velocities), the last layer tells them what actions to take and the middle 3 layers, called hidden layers, are where the calculations are performed to convert the inputs into actions. Each agent is given quite a lot of information about its body, they’re given everything that Albert was given in the last video (which I explain in great depth in this pinned comment kzbin.info/www/bejne/gpCXc4Oggad5aqcsi=HHv3vrmgIxUGo54f). Just like the last videos, the agents are trained using reinforcement learning. For each attempt an agent has, we calculate a score for how 'good' their attempt was and the training algorithm we used (PPO) makes small, calculated adjustments to that agent's brain to try to encourage the behaviors that led to a higher score and avoid those that led to a lower score. For this video there are 6 different ways each agent is rewarded/punished, and I tried to make these reflect our normal movements as much as possible. REWARD FUNCTION Movement: Each time the agent takes action we check to see how much closer the agent is to the target and we reward them proportional to that distance. If they move a lot closer to the target, they’re rewarded a lot, if they move away from the target, they’re punished. Limb Fatigue: This is the heart of the reward function for this video, every time an agent takes an action on a limb, we punish it proportional to the strength of the movement and the current fatigue of the limb (so if the agent moves a limb that’s already really fatigued, the agent is punished severely), then we increase the fatigue level of the limb based on how strong the movement was, and with each frame we slightly lower the fatigue of each limb to simulate the limbs resting. This reward is meant to simulate muscle soreness and encourage the agents to find the movements that are most efficient for their body design, but also make for more interesting gaits, since without this punishment the agents would all likely opt for a safe shuffle and avoid taking large steps. If you're still reading this, you're probably really smart and want to learn more about Albert, so make sure to join my discord server I just made where we can talk more about the details of Albert's AI! discord.gg/jM2WkNuBnG :) Limb Hit: I wanted to punish the agents for falling over, so any time a limb that isn’t a foot hits something it’s not supposed to hit (the ground, other agents, etc.), we slightly punish the agent, and we also slightly increase the fatigue on that limb. Abrupt movement: Each time the agent takes action we calculate the average velocity of their body and compare it to the average velocity of their body when they last took action, the greater the difference in these two values the more we punish the agent, since a great difference implies abrupt movement was made, something that generally is bad for our bodies. For anyone looking to make something similar to this, this reward is really important for smoothing out the final gait! Chest up: We give the agents a small reward whenever their chest/head is in the upright position, this helps the learning converge easier, without this reward the agents might never learn to stand up and instead just learn to crawl to the target. OTHER I only allowed the agents to make a decision every 5 game ticks, which made the movement look a bit more jagged than if I allowed them to make a decision every tick. I found if I allow them to make a decision every game tick it’s too difficult for them to commit to any proper movements, they end up just making very small movements like slightly shuffling forward instead of taking a full step. The 5 game tick decision time forces them to commit to their decision for at least 5 game ticks so they end up being able to take the less safe (but cooler to watch) large steps. Though you only see one version of these agents, there were actually 40 copies (so 200 agents) training simultaneously behind the camera in order to speed up the training process. Despite this, it still took my computer (threadripper 3960x, rtx 4090, 128gb ram) over 3 days to train/record! We're looking to hire people to help make these videos! If you're a talented Unity game developer you can apply for a full time position here forms.gle/ko54z1LQmZNUT9Vp8 And if you're a talented AI developer (ML-Agents), you can apply here! forms.gle/Uou1Vwb5Q9VccaAY7 We're looking for full time employees, but part time works too, what we're really looking for are skilled and passionate people, so feel free to apply if you're interested! :D Thank you so much for watching, and please, if you enjoyed the video or learned something, share it with someone you think will also enjoy it! :)

[@kjkjkjkjkjkjkjkloklm]

Your animations are great

[@dogedog2447]

Fr

[@nexolu973]

So long not see you How are you

[@Goblinvr64]

Pog

[@SquareBlock5]

I’ve been waiting so long, thinking you stopped making videos, thank you for your dedication!

[@Ax2u]

Purple was robbed! Constantly getting tackled by others, and starting on the disadvantageous side track with less space to manoeuvre... Where is the competitive integrity?! Red deserves a DQ for that awful, childish behaviour on run 912.

[@OmniSync]

and on run 1410

[@ankyloinc.]

They did my boy dirty 😢

[@Leon-br9yk]

ay dont insult my boy red

[@nevan2201]

YEAH #DQRED

[@Bluejaymare]

Exactly. red would always take it out on purple

[@darkacadpresenceinblood]

red throwing a tantrum in the middle of the track so now noone else can pass either was hilarious😭

[@RubyPiec]

Mood

[@Wholesome_love]

6:51 😂

[@OmniSync]

also on 8:45 💀💀

[@t4kumi704]

Typical bipedal behaviour if you ask me 😅

[@traionjones711]

AI don't have emotions so your comment isn't very funny.

[@kirkrowe2901]

This is amazing. I love Red's enthusiasm. "Yeah I love the high jump." "This is a race." "HIGH JUMP!"

[@Setter-the-tethering-boi]

Front flip

[@thanemullen8023]

I have never felt so disappointed to see a video end. I hadn’t been watching the time stamp, and I was so invested in seeing them (especially purple) reach the point that they were truly racing.

[@davidthecommenter]

i'm glad to see albert's knowledge of walking is being used to help teach balbert, gralbert, ralbert, yalbert, and palbert how to walk too!

[@neofalz7643]

Okey now its they canon name

[@tulliuscicero852]

in case i was the only one who saw it, the names are based on the colors of each one, for example yalbert is yellow and ralbert is red

[@ArThur_hara]

@@tulliuscicero852 noice :D

[@LucasGleason]

@@tulliuscicero852no way

[@LordDragox412]

@@tulliuscicero852 Yes, you were the only one who saw it, for you have special eyes. So look, look with your special eyes and spread your wisdom upon us, the unwashed masses! /s

[@BeanicusYt]

I can’t wait for all of these AI’s to get their own characters and lore. I can just imagine a cinematic universe for this channel Edit: how the HELL did this comment blow up

[@supercrazy7188]

Lol

[@froolsy]

Next video: ai fight club

[@alial3437]

This remembered me The Amazing Digital Circus.

[@chocolates_muffin]

We should make this just make a random backstory made by Chat gpt sounds good by my opinion

[@alex.g7317]

I guess, but I’m afraid content farms might yoink his idea and use these characters in the worst of ways :/

[@mlijah2730]

10:02 one must imagine purple happy

[@yonekobysura8440]

*intense Syphius music plays

[@mcdonaldswi-fi2720]

*Syphius picture fades in and out*

[@Grandremone]

PURPLE WON GODDAMNED

[@32zzo]

its sisyphus not syphius

[@ussrball1692]

@@mcdonaldswi-fi2720 bro switched account to recreate a meme

[@mf6610]

If these were developed into characters. Purple: Wild Card, Optimistic, Sometimes Lazy Yellow: Straightforward, Patient Red: Entitled, Whiney and Immature, Show-Off, But Very Determined Green: Quirky, Meek Blue: Clumsy, Curious -Purple often gets screwed over by others but stays determined -Red is slow to learn, behaves badly, and suffers from karma a lot

[@zacwoods]

Alright PacMan relax lol

[@sherryyoung3412]

good personification！

[@doctorchess801]

Red was the definition of character development Also purple being the Pixar lamp was funny tough

[@coolokayyeah]

It’s amazing how well the AI learns, even if it takes a while

[@RubyPiec]

It learns faster than us

[@9nikolai]

@@RubyPiec Did it take you more than 1638 attempts to learn to walk? Most people manage in a little less than that

[@RubyPiec]

@@9nikolai what counts as an attempt?

[@omphya6229]

​@@9nikolai the ai learnt to walk in 3 days, most people take about a year.

[@9nikolai]

@@omphya6229 The ai doesn't need to eat, sleep, or anything else than walk.

[@triplea007]

Starting positions should be randomised to give each ai a fair shot at learning. Loved the captions music choices.

[@jaden_playz805]

7:13 purple just “resting” 😭😭😭😭😭😭😭😭😭

[@Bacon_1672]

what

[@user-sr2nl4cn3f]

lol

[@melvint-p9500]

he's had enough

[@very.very.silly.]

he wasnt resting he was doing the deed to himself

[@buzzlightyearpfp7641]

you're actually revolutionizing the AI genre on youtube

[@ARockyRock]

you might be interested in carykh's evolution series

[@armyninja122]

yea

[@traionjones711]

Lol he hearted your comment. What a delusional loser. You really shouldn't hype up content like this. It's nothing special.

[@ryanchanghomosapiens6507]

Can we appreciate the fact that at 10:18, yellow turned around and walked backwards but still went super quick?

[@AsoGamer33]

yo he moonwalked

[@shreddy_fazchair]

699 likes... guess I'll be one to ruin it

[@EntergeticalakaBot]

700 likes... I guess I saw it happen

[@Xuebatt]

bro is twerking

[@Kinitopettheorist]

*HE HE*

[@rodlah6205]

10:30 when you try to run from a monster in a dream

[@bobblab]

Bruh💀💀

[@zackyep]

​@@bobblabbruh 🎉🎉

[@babyghast4379]

Before I watch this to the end, I am rooting for purple. I want to see the monopod win. (After watching it, second place ain’t so bad. They would have gotten it if they had an extra second or two.)

[@B-S-S-Iris]

Again, it was very interesting. I felt that when Red fell, it dragged everyone down and negatively affected the learning of those around him, so if the focus was on running, I felt it would be preferable to have him run the race alone and then composite everyone's movements in later editing, etc. I was rooting for Purple's run because it was so careful and beautiful... I still wonder if the longer length of one step is more advantageous? From a Japanese fan Translated by Deepl

[@ixiepeach6787]

Purple was the only who learned how to walk properly with one leg.

[@arthurfraco2970]

Exactly! After red started to fall consistently over purple track, purple unlearned how to hop.

[@wildfire9280]

@@arthurfraco2970 purple lost brain cells looking at red

[@ralmilk]

It was interesting to think about how some AI probably got steered in a less efficient direction because they were trying things and getting stuck on the other models. I wonder how differently this would have worked out if they couldn't bump into one another.

[@armyninja122]

yea sure is interesting

[@travisjohnson6703]

That's the fundamental limiter on all this deep learning stuff. The data set in reality is always messy and incomplete, which quickly leads "AI" down bad paths that living beings tend to suss out easily.

[@jffrysith4365]

@@travisjohnson6703 AI always faces this issue, it frequently randomises to local better locations that are actually globally worse. This is easily fixed using general annealing algorithms etc. that tend to be used in most complex AI systems.

[@dazedazedazz2939]

Now I just want to see these five AI’s learn how to work together…Similar to Albert’s puzzles!

[@skevoid]

Having collision between the different agents adds a level of randomness that seems like it would severely hamper the learning progress.

[@billy4301]

but falling is funny

[@Pyro03333]

I love how you treat each AI as if they were your child. Your channel is just really wholesome.

[@mjvafadar2526]

He casually mentioned the fact that they made it in a way which they're in great pain when they fall and you're calling it wholesome😂😂

[@Pyro03333]

@@mjvafadar2526 true. I forgot about that.

[@wildfire9280]

@@mjvafadar2526 Spare the rod, spoil the child. (Disclaimer: Do not actually follow this.)

[@mythbusterman8541]

Red’s movements resemble those of the character from that QWOP game ungainly and spectacular spills. The way he sabotages the rest of the athletes inadvertently or otherwise in the process of tumbling is outstanding .

[@TrueLadyEvilChan]

5:01 Red: I call this the QWOP shuffle

[@RRVCrinale]

Fun fact: that hop Red does isn't too dissimilar from the way astronauts bounce around on the Moon. It's also essentially Purple's locomotion, for that matter.

[@cecilebraillie4471]

5:20 purple _deliberately_ throws itself on yellow in the hope to piggyback along 😊😊

[@regularrobloxtuber]

I love how he colors some of the words red if the AI does something bad , Yellow if its okay And green if its excellent

[@MalarkySparky]

Do you think it would've run differently if they were encouraged more to stay in their own lanes?

[@meizuman]

Yeah

[@yuhyuh2412]

prob for purple

[@beardedshuckle5220]

I just appreciate that the victory was done with a john cleese silly walk

[@Vd_124]

This made my day, thanks 😂 i’ve been searching awhile for something that could cheer me up

[@sergimeli4194]

I honestly felt so surprided purple performed so well. I though it want going to be able even to stand up. Amazing video as always!!!

[@debadityanath4398]

purple had the advantage of less parts, and less learning and tweaking

[@siraaron4462]

There's a reason worms and fishes evolved first.

[@dimglow]

11:09 you lied about the cake, now he's crying 😭

[@AltoRed_]

IEIEJEHED THE CAKE IS A LIE THE CAKE IS A LIE THE CAKE IS A LIE THE CAKE IS A LIE THE CAKE IS A LIE THE CAKE IS A

[@zhantaufik]

He really looks like he is hysterical

[@delta1234s]

The cake is a lie 🎂

[@ThisManlyFlower]

too little people catching that obvious portal reference lmao@@delta1234s

[@Jared_24]

LOVE this Content. Its different to all this junk on KZbin. This is ACTUALLY Entertaining!

[@cobusvanderlinde6871]

Red definitely figured out how to maximize his reward by diving forward the moment he loses balance. Would be really interesting to see how competitive this would get if the ai are all allowed to fully mature into sprinting masters. Assuming red would still end up winning with those long legs, but the others might put up some impressive competitive performances.

[@redthered279]

Red also learnt to stay on top by hindering the other agents' movements, causing their learning to be sabotaged and set back. Smart but dirty.

[@cobusvanderlinde6871]

@@redthered279 I doubt it got rewarded for that at all. I do not remember any indication that the ai were getting rewarded for overall placement, just for personal achievement.

[@burningtank160]

They are not identical, they are each special in their own way 😁

[@doob.]

i am special

[@MJRuda]

​@@doob.yes

[@ChronoNewton]

​@@doob.yes

[@OriginalRadEdits]

@@doob.yes

[@steelsalmon9121]

@doob. yes

[@conwarlock3537]

9:21 That's a pretty solid frontflip. Maybe you could do some challenge in that direction too?

[@keithledbetter9132]

Funniest thing I've watched all year by far Really enjoyed this work

[@Jammybobs]

No way youtube geniuinely recommended a good youtuber for once. Can't wait to see Albert learn more and more (and maybe make some friends along the way?) :)

[@RasmusBerggren-uo6uu]

I love that red is walking around like a extremely drunk person and how he randomly keep bullying the others like purple or green. Truly a drunk Florida man

[@DadGamesGood]

Even though you hilariously mention the AI being in pain, I think your videos really open up peoples eyes to the opportunity that AI presents in an educational and entertaining way. Well done my friend keep these awesome videos coming, I can't imagine the work that goes into them!

[@miriamkapeller6754]

It makes sense to compare the scoring methods used in reinforcement learning to pain and dopamine release in animals and humans, as there are many similarities. They also have similar pitfalls, for example an AI can have a traumatic event where they had a very bad experience with something and will never attempt to do it again, even though it could be beneficial. And just like humans, an AI can get addicted to things that serve no actual practical purpose because it keeps getting a hit of dopamine. If you think about giving negative and positive scores to your agent as pain and dopamine, the behavior of your agents will likely make more sense to you.

[@GenocideLv]

its important to not humanize AI. They are already working on propaganda movies of "AI children". Its a big step for transhumanism, and cant be allowed

[@pizzainc.1465]

HAHAHA 5 AIs IN EXCRUCIATING PAIN SO FUNNY

[@kacp6485]

What the heck does it mean that robot is in pain??

[@pizzainc.1465]

The robot is being punished. Punishment for AIs works in a similar way to pain for us, because it lets them know that something is wrong, they do whatever they can to fix it, and their entire life’s purpose is to reduce punishment.@@kacp6485

[@mushroomng1739]

9:45 just for myself like a bookmark

[@Sourcecodemastergoaheadcheater]

Albert your working so hard and becoming wiser by the seconds. I want to find out what you're all good at or like doing and i want to help your dreams kids❤❤❤

[@enderjed2523]

If you ever do another one, here's my suggestions: 1. Make the AI not collide with eachother, this will avoid dirtying the training set. 2. You could try using the old Albert agent/model (or other old agents/models) as a comparison 3. And in terms of ideas for other models, you could try a 6 or 8 legged model, alongside a spring-esc/jellyfish model that I've seen in old Framsticks simulations

[@pitori.]

Those are all cool ideas Exept for the first one cuz funni

[@enderjed2523]

@@pitori. It reduces comedy, sure, but it's more scientific. Besides, in final races the collisions could be turned back on.

[@womp47]

@@enderjed2523 how would they be able to adapt? they should be able to learn with collisions, and need to adapt to the other contestants

[@c3caine]

its funny watching them crash@@womp47

[@Isperada]

​@@womp47 depends on how they set it up. If they put in inputs that tells the AI that they collided with other AI then they might be able to handle it. However if they didn't the AI will have no clue that they were being interfered with and just believed what they were doing was wrong, even if what they were doing would have got them further, making them unlearn their improvements.

[@alantyto3627]

Gosh I absolutely adore these tiny AI buddies. I can almost see their personalities. Watching them go from confused wobbly wormies to successful walkers and jumpers is extremely entertaining! Your commentary is, as always, brilliant. Just like the joke in the end :) I do wonder though what happened to the rest of the team who was not able to make it to the finish line. Guess they're on the AI vacation where they're rewarded for simply lying around 😂 Also a huge thank you for the thorough explanation of your work, it's really interesting to read! Good luck in your further work, I'll look forward to the new video!

[@Cl-2048]

No theyre in a butterfly farm upstate

[@DasSystemschaf]

LOL, that was so funny. My wife also enjoyed watching it. Thx for sharing.

[@Wallibear]

can we appreciate the effort albert puts into these videos

[@tainted2141]

Noooo wallibear became an ai

[@ethanlong1075]

Didn’t expect to see you here!

[@traionjones711]

Minecraft youtubers annoy the hell out of me ngl

[@traionjones711]

Can we appreciate the lack of effort this waste of space puts into the garbage slop he calls content?

[@traionjones711]

Also Albert is the channel mascot, not the channel owner. Moron 🤣

[@Blyat98]

To be honest, the test rooms always made me think about the game portals. That cake reference was amazing!! Love your humor in your videos. This one was amazing!! Keep going!

[@Jaqubix]

This video taught me that by tackling others you can slow down their development and win over them

[@adamusprime403]

You lying about the cake feels like a revenge plot against Glados

[@WalrusQuake]

I noticed that since the separate AI models can collide with eachother and start each run with relatively the same behavior as the previous, an AI could use another's strategy to create an advantage for themselves. I noticed red started to lean on yellow around 2:50 to get a boost.

[@chrisvdmeer]

yeah if they would have trained seperately it might have been different.

[@b_2the_boy551]

Yeah just like how purple tried to ride yellow in 4:18 😂

[@ArgoFlex]

The green one 💀

[@Jeykit0]

The purple one..

[@centralmask8947]

Lol

[@frosgare]

@@Spamtinglecommitting public indecency with red

[@user-mc9es6tw5g]

1:03 red was doing planks this shows he go's to the gym

[@cytrynekzoty8508]

purple: hop hop yellow: slow but steady red: "watch me do a frontflip" green: yellow blue: "hello where is the finish"

[@lolnt6103]

4:18 Purple learns horse riding

[@user-jd3gf5xw1x]

8:35 bruh this scene out of context xD

[@carter.5814]

I love these videos keep this up!

[@hungryironapple]

green knew exactly what he was doing 3:12

[@tomvr4543]

TOO DEEP AI LEARNING 😂

[@Memeened]

Kinda sus

[@CentroBBerry]

“You’re kind of flopping around like a worm” What do you expect? You gave him the body of a worm!

[@uma_pessoa.aleatoria6902]

Wow, these AI videos are great when the video finished i just saw that there more about AI its so cool

[@sjdpfisvrj]

This video perfectly illustrates the dirty secret of Reinforcement Learning: it is not all that far from Brute Force.

[@Kram1032]

incredible. I fully predicted the others would learn this much sooner than red simply because it's by far the most complicated body. But I guess the size of its leap, once it can finally leap, simply makes up for all the difficulty of learning to leap! And by the end it's even a *sort of* natural motion. Like, not really, but at least it's imaginable that somebody would intentionally walk in an incredibly silly ways.

[@sarahmellinger3335]

it's like a horse's gallop with springy foot joints

[@beardalaxy]

He might even get invited to the ministry.

[@amberslime3683]

The 100 Meters AI Race - A Summary of the Competitors (From 1 to 5) (Contains Spoilers) *Purple* Purple is the one-legged fellow with one eye. They have a major, major problem with balancing, one that prevents them from actually being able to race most of the time. When the stars align and Purple is actually able to begin racing, they use swift short hops that are remarkably consistent... so long as he doesn't bump into anything. *Yellow* The quadruped. Yellow was the first AI to figure out how to properly race, and has proven to have the most stable gait. Once Yellow figured out how to walk, there was nothing that could make him fall over that I could recall. Unfortunately, Yellow is extremely slow, and unless we're talking about a competition between tortoises and hares, slow and steady *does not* win races. Yellow also has this strange obsession with walking along the fence. *Red* The one who's form mimics that of Albert, the Most Heavenly and Holy Strider. Red has precisely none of Albert's grace and coordination, having a false-start rate that's as bad as or perhaps even *worse* than Purple's. When Red does manage to figure out how to use the holy form they were blessed with, they use either some sort of strange tip-toeing walk or big, lunging gallops. *Green* The tripodal unit. Green is just behind Yellow when it comes to stability, and just ahead of Yellow when it comes to speed. Green's most notable accomplishments include being the second one to figure out how to stand stably and that one time they got stuck doing a headstand. *Cyan* There's a fifth racer? What're you talking about-- Oh, that one! Yeah, Cyan is shaped sort of like a Goomba, essentially a head and two legs. Cyan... look, Cyan might as well not even be there. They have one notable trait, and that's that they tend to walk down off of the track assuming that they go on for long enough. *And the Winner is...* RED! W-Wait, Red? The one who can barely even stay upright even though they've got two legs, two arms, and the inherent holiness of Albert's form? That guy? Huh, okay... I can only assume that it was the aforementioned holiness that allowed Red to win... or maybe it's because they had the longest stride? It's one of the two...

[@ToastOnMyFace]

Wow

[@AnimationsAndOtherStuff]

Red's also a big crybaby who loves taking his anger out on others, especially Purple

[@name6953]

I was upset too because Purple was stopped when he was just about to win :(

[@BadFeelingsClan]

I wonder if, when AI finally enslave us, they too will give us difficult tasks to perform in exchange of pastries, just to laugh at us. And when we finally succeed, against all odds, they will not give us cake. You're setting a dangerous record, my friend.

[@wickmilla]

4:38 blue crying on the floor

[@black_circle322]

Green seems worried about red.

[@wickmilla]

didnt notice that😂

[@NotLegallyAGeologist]

blue is down pounding his head against the kitchen floor

[@imaMONKE725]

red was so smart, messed up the others so that their good habits weren't rewarded as they wouldn't get far due to the red's sabotage, meanwhile red couldn't be sabotaged and could learn without major problems

[@its_Hazer]

I smell someone's boutta make an amogus joke

[@luchirimoya]

​@@its_Hazerin 2024? I sure hope not 😭

[@jasonjoshuapeters8955]

Its because red learned the way albert learned

[@redthered279]

Red sabotaged the others?? amogsus reference??

[@imaMONKE725]

@@redthered279hazer was right all along

[@xeniaxxainex]

Personally I am thrilled with your videos. Could you tell us, if you haven't already done so in some comments, which tools you used for these simulations? That is, what software and/or programming language and library? Thank you very much and congratulations!

[@Jyaacho]

Red the funniest lil dude, every sinle time he fell over the barrier I bust out laughing.

[@ballingcuber1170]

I was rooting for red from the start and honestly halfway through I thought I made the wrong decision, but when that man came jeeping and juking thru the other competitors on good pace and crossed that 100m mark. I cried a tear of joy

[@eugenioreale7588]

no bro im sorry he removed from the video the part where purple won :(

[@gamerits]

gaslighting is real

[@everesthines2228]

@eugenioreale7588 no, Purple didn't reach the end in time. Red won.

[@jxton_]

​@@eugenioreale7588purple didnt win it ran out of time 💀

[@ItsJustKiro]

@@eugenioreale7588 purple didnt win bro, he ran out of time

[@chadwickpuffington]

As a parent of a toddler i felt this.

[@fragmented_dreamz327]

I've always wanted to experiment with AI like this, what program or how do you even accomplish something like this?🤔

[@inakymino3278]

0:22 ALBERT

[@VB4VB4]

real!!!11

[@caominh8622]

OMG ALBERT STEAL CAKE!!

[@croassung3721]

*ALBERT*

[@Mar_Marine]

This was an absolutely delightful video! It was extremely entertaining how each body took a unique personality - I found myself rooting quite a lot for Purple as they really put the effort in! I can't wait to see Albert's return, and maybe the return of our newfound friends here.

[@glitchon7151]

i mean albert DID escape.

[@ArmoredarmadilloX]

Purple was my hero in this, So much was against the lil guy, yet he made great strides, figuratively and literally.

[@Spookweave]

Red's antics had me laughing all throughout the video

[@joe_z]

5:00 Red found his inner QWOP.

[@Alan_Thingz]

11:00 The cake is a lie.

[@SuperBee3]

Small detail. The cake is shiftted.

[@GDnobrain]

NOOOOOOOO

[@Dofor]

@aiwarehouse Regarding the 40 copies of the simulation running behind the scenes, when updating the policy through PPO, do you aggregate and consider the experiences from all 40 to inform the policy adjustments, or is the update based predominantly on the best-performing instance among them?

[@Chronolinth]

Red's character development is absolutely beautiful

[@AidanDaGreat]

I kinda like the idea for the lore: an all-powerful being, believed by the others to be Albert, cruelly creates amalgamations of coded flesh, forcing them to attain meaningless goals for their own entertainment. But what if, with bonding with each other through harrowing and wacky experiences, the AI realized their true power, and who really is the TRUE creator? The mind boggles. Amazing video!

[@Snai1poster]

Red trying his hardest to be the favorite child

[@aiwarehouse]

Thank you so much!!:D Red may have tried his hardest but nothing compares to Purple

[@crodzilla]

Another fantastic example of deep reinforcement learning. Great job! Keep it up. I hope you are able to share your information and methods one day.

[@Spirit_Matters.Arthur]

I just wish to thank God for the Natural Intelligence we were given to be way faster and more efficient learners then any AI can ever be! Instinctual for the Win

[@blobbo.]

THE KING IS BACK!!!

[@mrhalfsaid1389]

I love how you can never really tell who will win these, plus its funny how the approaches they take give each ai personality in there own... interesting ways

[@bristratostar7908]

Your billboards and advertisements are hilarious, so bad 😂😂😂❤

[@daxramdac7194]

This was really cool. What amazed me is how, by the end, Red basically almost solved walking. Of course it was wonky, awkward, and unstable, but the fact that it was closing in on the right solution for bipedal walking is fascinating.

[@MochiWrath]

4:50 he fell due to shock

[@lennard3042]

Yay finally another video, it's just unfortunate that they take so long to make I also am trying to make my own walking ai and i also am planing to (hopefully) make it working phisical body, so these videos always are a great help and inspiration for me, keep it up!

[@FunIsGoingOn]

I don't care if this actually includes AI, but the production quality, the comments and music, easily the most funny 11 minutes of the year, so far. 😂😂😂

[@mattjpoolr]

Love this ❤

[@braedenwilson6374]

I'll be honest, I saw the first video about a week after it came out, and I've wanted more ever since. I hope you get the recognition you deserve! (been playing this video on repeat about 10 times now, hope that helps your algorithm!) Definitely my favorite AI channel out there!

[@triigrr3644]

Absolutely love your videos. The AI concepts, editing and ultimately the project execution/idea is amazing.

[@triigrr3644]

Would rewarding AI’s with new limbs in the future to accompany their current brain power, in some type of tournament style, be an idea you’d like?

[@gravamante]

We missed you. Your videos are quite original despite how few they are. Is not the amount, it's the effort 🎉

[@davidunkown1925]

Probably should have created 5 seperate simulations that also reward staying in lane to incrntivize directional consistency and remove unnecessary interference to build up the movement models before adding them all together, but still enjoyable to watch.

[@Collins6769]

At 8:10 I love that green came up to the skill of breakdancing 😂

[@Incineration72]

Green prob like "screw running i wanna dance"

[@TGood1e2]

This was so worth the wait, thanks for showing us this masterpiece!

[@bendubz9000]

I'd call this proof of concept that we all learned to play QWOP the same way Red did. Lots of front leg shuffling, it's just the best way for a bipedal model to do it

[@marksmith5754]

4:26 had me 💀

[@Sharivari]

This video ended way too soon. I could have watched way longer. So interesting, and such good storytelling Love it!

[@ObviouslyASMR]

Loving your videos dude! It would've been really cool to see a graph either showing the rolling avg distance or the best distance so far for each colour over the generations, to compare how the competition is progressing at any time

[@VirtuoVR]

I remember seeing this channel when it was super small, crazy man, awesome vids ❤

[@creepermakes2677]

The cake is a lie