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 UA-cam 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 ua-cam.com/video/L_4BPjLBF4E/v-deo.htmlsi=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! Thank you so much for watching! These short videos take literally hundreds of hours to make, if you want to help allow us to make them faster, please consider becoming a channel member! By becoming a member, your name can be in future videos, you can see behind-the-scenes things that don’t fit in the regular videos, you can also use stickers of Albert, Kai and some other characters our team made in comments (more coming) :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! :)
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.
@@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
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.
Congratulations, the test is now over. All Aperture technologies remain safely operational up to 4000 degrees kelvin. Rest assured that there is absolutely no chance of a dangerous equipment malfunction prior to your victory candescence. Thank you for participating in this Aperture Science computer aided enrichment activity. Goodbye.
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
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
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!
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.
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.
@@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.
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 .
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.
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.
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
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
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!
I like how the fact purple proved that no matter how many obstacles. Dangers. Or things like being tackled.. He still kept goin and got very close to the end... Purple be strong bro
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
@@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.
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.
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!
I see an issue here. How is the four-legged one being punished? It's almost impossible for it to fall over. It may make it less efficient at recognizing what NOT to do.
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.
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...
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!
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.)
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
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
Thats whats incredible, I love it. And as programmer I know that this could take months of work, so I hope this little tip help you to keep doing this beautiful job.
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
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
Oh, and also, I'm so glad you ended up using a muscle fatigue system, as I was explaining to my friend, is one of the main factors we walk the way we walk today. So, very interesting!!!
it seems that red, blue, and purple were all using the same hopping technique. Purple was able to hone the technique first because they didn't have other limbs to focus on, but that fact also meant they did not have any other limbs to use for balancing. Blue had one other limb to balance with, put presumably because it is so short it was not able to travel very fast, and having only one extra limb seems to prevent it from being able to steer. Red was taller and had three extra limbs. which is why it was so fast and successful.
Cool. I was hoping the video would keep going and show how all their movements ended up once they cleared the challenge and how much training the different bodies needed. It makes sense to end the video where you did but I wouldn't mind a Bonus video showing some more
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 UA-cam 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 ua-cam.com/video/L_4BPjLBF4E/v-deo.htmlsi=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!
Thank you so much for watching! These short videos take literally hundreds of hours to make, if you want to help allow us to make them faster, please consider becoming a channel member! By becoming a member, your name can be in future videos, you can see behind-the-scenes things that don’t fit in the regular videos, you can also use stickers of Albert, Kai and some other characters our team made in comments (more coming) :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! :)
Your animations are great
Fr
So long not see you
How are you
I’ve been waiting so long, thinking you stopped making videos, thank you for your dedication!
epic
Purple's idea to piggy back on yellow was genius, I wish they kept developing that pattern.
To clarify purple piggybacked yellow on 4:17
The purple invented ai riding
I think purple stopped doing it bc I saw in the pinned comment that they get punished for touching each other
Purple just invented parasitism
But the video creator didn't really see the interesting side of this, instead just made another crappy joke.
red throwing a tantrum in the middle of the track so now noone else can pass either was hilarious😭
Mood
6:51 😂
also on 8:45 💀💀
Typical bipedal behaviour if you ask me 😅
AI don't have emotions so your comment isn't very funny.
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.
and on run 1410
They did my boy dirty 😢
ay dont insult my boy red
YEAH #DQRED
Exactly. red would always take it out on purple
9:16
"This fence won't stop me!"
Ahh flip 😭🙏
real
He was on a mission fr xD
me when the judge hasn't gotten her daily hug:
9:20
bro wanted to see if leaping was a good option
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!
Okey now its they canon name
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
@@tulliuscicero852 noice :D
@@tulliuscicero852no way
@@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
This is amazing. I love Red's enthusiasm.
"Yeah I love the high jump."
"This is a race."
"HIGH JUMP!"
Front flip
3:13 FREE BJ
Purple should have win, Red always kick him
Nah red deserved that win
@@progamr4025 he really didnt.
"Throw a baby into a pool and it will learn how to swim" - the first data scientist probably
This video taught me that by tackling others you can slow down their development and win over them
It made me laugh my heart out especially red’s silly shenanigans
In short , cheaters always win is what we learn from this xD :)
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.
lol
Red was the definition of character development
Also purple being the Pixar lamp was funny tough
THE CAKE IS A LIE!
I see you are also a person of culture 😉
Yeah, but Red will be making a note here
"HUGED SUCCESS"
I said that and then this comment popped up. What a coincidence!
Congratulations, the test is now over. All Aperture technologies remain safely operational up to 4000 degrees kelvin. Rest assured that there is absolutely no chance of a dangerous equipment malfunction prior to your victory candescence. Thank you for participating in this Aperture Science computer aided enrichment activity. Goodbye.
Portal refrence
you're actually revolutionizing the AI genre on youtube
you might be interested in carykh's evolution series
yea
Lol he hearted your comment. What a delusional loser. You really shouldn't hype up content like this. It's nothing special.
Can we appreciate the fact that at 10:18, yellow turned around and walked backwards but still went super quick?
yo he moonwalked
699 likes...
guess I'll be one to ruin it
700 likes...
I guess I saw it happen
bro is twerking
*HE HE*
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
Purple was the only who learned how to walk properly with one leg.
Exactly! After red started to fall consistently over purple track, purple unlearned how to hop.
@@matheusnunes970 purple lost brain cells looking at red
100% I feel they could have just changed one variable to make them not collide with each other and it'd be even better
My dumbass thought you were an electric fan from a Japanese company
0:21 HELLO ALBERT >:D
10:02 one must imagine purple happy
*intense Syphius music plays
*Syphius picture fades in and out*
PURPLE WON GODDAMNED
its sisyphus not syphius
@@mcdonaldswi-fi2720 bro switched account to recreate a meme
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
Lol
Next video: ai fight club
This remembered me The Amazing Digital Circus.
We should make this just make a random backstory made by Chat gpt sounds good by my opinion
I guess, but I’m afraid content farms might yoink his idea and use these characters in the worst of ways :/
I love how you treat each AI as if they were your child. Your channel is just really wholesome.
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😂😂
@@mjvafadar2526 true. I forgot about that.
@@mjvafadar2526 Spare the rod, spoil the child.
(Disclaimer: Do not actually follow this.)
3:12 green was having a bit too much fun there 💀💀💀
Ayo
Ayo
Ayo (chain please)
Ayo💀
Ayo
It’s amazing how well the AI learns, even if it takes a while
It learns faster than us
@@RubyPiec Did it take you more than 1638 attempts to learn to walk? Most people manage in a little less than that
@@9nikola what counts as an attempt?
@@9nikola the ai learnt to walk in 3 days, most people take about a year.
@@omphya6229 The ai doesn't need to eat, sleep, or anything else than walk.
can we appreciate the effort albert puts into these videos
Noooo wallibear became an ai
Didn’t expect to see you here!
Minecraft youtubers annoy the hell out of me ngl
Can we appreciate the lack of effort this waste of space puts into the garbage slop he calls content?
Also Albert is the channel mascot, not the channel owner. Moron 🤣
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!
11:05 bro is gonna get a villain arc
😭😭😭
He looks like he starts to cry
Yeah he covers his eyes bruh @@TABtheomeletteguy
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.
yea sure is interesting
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.
@@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.
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 .
5:01 Red: I call this the QWOP shuffle
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.
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!!!
purple had the advantage of less parts, and less learning and tweaking
There's a reason worms and fishes evolved first.
Did anyone else notice the sign that said “fall down? Get up. Ai medical insurance” 😂😂😂
Yes i laughed my head off 😂
@@CurtisAtkinson-u2x yeah! I did too
Do you think it would've run differently if they were encouraged more to stay in their own lanes?
Yeah
prob for purple
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.
yeah if they would have trained seperately it might have been different.
Yeah just like how purple tried to ride yellow in 4:18 😂
9:21 That's a pretty solid frontflip. Maybe you could do some challenge in that direction too?
Lol stupid red AI
Its like a baby just born to race@@Soeasywhat
11:11 red had a temper tantrum after realizing the cake was fake
The cake was a lie "red 2024"
He did all of that for nothing
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
Alright PacMan relax lol
good personification！
albert is albert, he is the eldest of them all and the most learned
This... this is literally the color gang from alan becker
@@drawnwithlove3499 bro, literally what i was about to type xd
Starting positions should be randomised to give each ai a fair shot at learning. Loved the captions music choices.
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
Red is an ai florida man in disguise
Love how Albert (Orange guy at the end of the race, protagonist of al the other videos in this channel) is just chilling at the end
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!
No theyre in a butterfly farm upstate
Red trying his hardest to be the favorite child
Thank you so much!!:D Red may have tried his hardest but nothing compares to Purple
By the way, what was green doing?
At 3:12 😏
They are not identical, they are each special in their own way 😁
i am special
@@doob.yes
@@doob.yes
@@doob.yes
@doob. yes
I like how the fact purple proved that no matter how many obstacles. Dangers. Or things like being tackled.. He still kept goin and got very close to the end... Purple be strong bro
11:09 you lied about the cake, now he's crying 😭
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
He really looks like he is hysterical
The cake is a lie 🎂
too little people catching that obvious portal reference lmao@@delta1234s
9:14 was a PERFECT music buildup
FRFRFRFRF
7:13 purple just “resting” 😭😭😭😭😭😭😭😭😭
what
lol
he's had enough
he wasnt resting he was doing the deed to himself
Blue though
3:13 NAH GREEN GETTING FREAKY
He's giving head
So that wansnt a third leg...
He’s trying to get that motivation 💀
freakgreen is calling👅💦💦
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
Those are all cool ideas
Exept for the first one cuz funni
@@pitori. It reduces comedy, sure, but it's more scientific. Besides, in final races the collisions could be turned back on.
@@enderjed2523 how would they be able to adapt? they should be able to learn with collisions, and need to adapt to the other contestants
its funny watching them crash@@womp47
@@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.
10:30 when you try to run from a monster in a dream
Bruh💀💀
@@bobblabbruh 🎉🎉
frrr
Relate, I couldn't even stand properly
4:53 I love how purple just looks at the 40m sign and went "yippe!" then fell down
4:52 "im tired i need rest"
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.
THE KING IS BACK!!!
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
6:50 Red kicking Purple is the funniest thing I've seen today
“You’re kind of flopping around like a worm” What do you expect? You gave him the body of a worm!
The green one 💀
The purple one..
Lol
@@Spamtinglecommitting public indecency with red
Is here
creeper
Now I just want to see these five AI’s learn how to work together…Similar to Albert’s puzzles!
6:57 red is the imposter! He sabotaged purple! 😂
at least green helped purple
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!
4:18 Purple learns horse riding
8:35 bruh this scene out of context xD
I see an issue here. How is the four-legged one being punished? It's almost impossible for it to fall over. It may make it less efficient at recognizing what NOT to do.
Came here for this comment.
As a parent of a toddler i felt this.
Of what....? Green with Red doin or exercise
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.
it's like a horse's gallop with springy foot joints
He might even get invited to the ministry.
11:00 The cake is a lie.
Small detail. The cake is shiftted.
NOOOOOOOO
Not many portal players here, as it seems.
it was in one of his vids too
guts and blackpowder animater commento in ai race momento
Edit
9:21 red’s strategy: *F R O N T F L I P*
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...
Wow
Red's also a big crybaby who loves taking his anger out on others, especially Purple
I was upset too because Purple was stopped when he was just about to win :(
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!
This video ended way too soon. I could have watched way longer. So interesting, and such good storytelling Love it!
I love these type of videos. I hope you make it to 1 million subscribers.
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.)
Having collision between the different agents adds a level of randomness that seems like it would severely hamper the learning progress.
but falling is funny
This made my day, thanks 😂 i’ve been searching awhile for something that could cheer me up
11:00 The cake is a lie.
GLaDOS: I'm proud of you Human.
LOL
I just appreciate that the victory was done with a john cleese silly walk
This was so worth the wait, thanks for showing us this masterpiece!
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
I smell someone's boutta make an amogus joke
@@its_Hazerin 2024? I sure hope not 😭
Its because red learned the way albert learned
Red sabotaged the others?? amogsus reference??
@@redthered279hazer was right all along
6:46 I love how a brawl just broke out. xD
10:00 THAT WAS TRAGIC
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
no bro im sorry he removed from the video the part where purple won :(
gaslighting is real
@eugenioreale7588 no, Purple didn't reach the end in time. Red won.
@@eugenioreale7588purple didnt win it ran out of time 💀
@@eugenioreale7588 purple didnt win bro, he ran out of time
Absolutely love your videos. The AI concepts, editing and ultimately the project execution/idea is amazing.
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?
Thats whats incredible, I love it. And as programmer I know that this could take months of work, so I hope this little tip help you to keep doing this beautiful job.
Wow, thank you so much!!:D
You are amazing!
That a much dollar
Red literally just embodied one of the most popular flash games in history to win the race
Not the video we expected, but the video we needed
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
LOL, that was so funny. My wife also enjoyed watching it. Thx for sharing.
Purple is the definition of defying God. He’s been spawned in a cruel game with minimal equipment yet he fights hard and gains ground.
Idk how your videos can make me giggle and even laugh so much which I haven't been done for quite a while. Loving your works keep it up my dude
5:00 Red found his inner QWOP.
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
I love these videos. I laugh so hard. ONE OF MY NEW FAV UA-camR!
LOVE this Content. Its different to all this junk on UA-cam. This is ACTUALLY Entertaining!
green knew exactly what he was doing 3:12
TOO DEEP AI LEARNING 😂
Kinda sus
8:10 Let green live his dream as a tripod instead of making him race!!
Good effort Blue, you will get them next time!
Green and Yellow are trying to stop Red bullying Purple while Blue just casually minds his own business
6:55 i like how green looks like as if he is really concerned for purple
@LeenaTheChessPlayerVanTongreen was tryna give him that red treatment
@@HollowHead._.lol
Grape duo is always canon.., sigh
Respect to Purple. He made a real competition with Red, even take in account that he has less options to run, or to run faster
7:21 I like how hitting 60m is literally hitting 60m
Oh, and also, I'm so glad you ended up using a muscle fatigue system, as I was explaining to my friend, is one of the main factors we walk the way we walk today. So, very interesting!!!
0:22 ALBERT
real!!!11
OMG ALBERT STEAL CAKE!!
*ALBERT*
ALEITHCBERT
CAKE AT STAKE!!1!1!1!1!1!1!1!11!!1!11!1!1!1!‽1?1!1!1!1!1!1!1
a human lying about cake to an ai? how the turntables…
delightful video as always !
it seems that red, blue, and purple were all using the same hopping technique. Purple was able to hone the technique first because they didn't have other limbs to focus on, but that fact also meant they did not have any other limbs to use for balancing. Blue had one other limb to balance with, put presumably because it is so short it was not able to travel very fast, and having only one extra limb seems to prevent it from being able to steer. Red was taller and had three extra limbs. which is why it was so fast and successful.
Cool. I was hoping the video would keep going and show how all their movements ended up once they cleared the challenge and how much training the different bodies needed. It makes sense to end the video where you did but I wouldn't mind a Bonus video showing some more