This 8 minute video took over 100 hours to make! Everything in the video (except for the music) was created entirely by me using Unity, so please, like and subscribe!:D 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 Albert: Time it Took to Train: Room 1: 10 minutes Room 2: 20 minutes Room 3: 29 minutes Room 4: 48 minutes Room 5: 5 hours 42 minutes Total Training Time: 7 hours 29 minutes *NOTE* You only see one Albert in the video, but there are actually around 50-100 copies of Albert and the room he's in behind the camera training simultaneously. This makes it so instead of me needing to go through 500 hours of footage to edit the video, I only need to go through 7. Albert was trained using reinforcement learning, meaning he was rewarded for doing things correctly (like hitting a pressure plate), and punished for doing them incorrectly (like falling off the platform or hitting a wall/obstacle). After Albert finishes each attempt, the actions he took are analyzed and the weights in the neural network (Albert's brain) are adjusted using PPO (proximal policy optimization) to prioritize the actions that lead to a positive outcome, and to avoid the actions that lead to a negative outcome. All of Albert's inputs is his 'vision', which comes from raycasts. There are a total of 21 raycasts, 7 looking down, 7 looking straight ahead and 7 above his head, all with a maximum FOV of 70 degrees to try to mimic our own vision. Each of these raycasts is responsible for 2 inputs for Albert's neural network; the distance to an object (if any), and the type of object it is (pressure plate, obstacle, ground). I also stacked Albert's vision 6 times so he can have some sort of short term memory, he can find a pressure plate in the room then take actions to get towards it even if it's no longer visible (for a little bit). 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 :) In the first room Albert starts off randomly making moves until he accidentally hits the pressure plate to open the door, giving him a reward. This reward made the neural network controlling his actions update to try to replicate that outcome, and this continued with each pressure plate until Albert opened the door and was able to walk (on an invisible pressure plate) in the next room. Once Albert got into the next room, the same process was repeated, continuing with the same neural network that let Albert escape the previous room. For people who think I faked this: It would probably take me longer to fake this than it would to just do it for real, I used Unity's ML-Agents toolkit to make it easy, though I have experimented before with doing everything from scratch (poorly). The reason this AI is a lot smoother than others you've probably seen is because I only allow the AI to make a decision every 10 academy steps (game ticks), so when it starts to turn for example, it's forced to keep turning that way for 10 ticks. I did this because I don't like how jittery the AI looks when you let it make decisions every tick. Also, you only see one AI in the video, but behind the camera there are roughly 50-100 copies of Albert and the room he's in that train simultaneously to speed up the training process. The reason I opted for this over having them all train in the same room is because I wanted to be able to follow a single character for the sake of the video. Albert uses the same neural network the entire time, all you need to do is add "--resume" to the end of the command when training in Unity to have it continue using the same brain. Unity's ML-Agents makes AI quite easy! 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 If you have other ideas for what I should make Albert learn how to do, please let me know!:D
@mothgyaru31582 жыл бұрын
Dude this is insane, it’s amazing! Do you think you could try and teach Albert some other puzzles, like where he has to push something into another thing or go through a maze? You’re a madlad for this
@thatguy-uc1hy2 жыл бұрын
Great video! But now make a dark Albert that gets rewarded for stopping Albert 😈, idk if that's possible just a off the top idea have a great day though!
@LuaTech2 жыл бұрын
This is awesome! I can't wait to see more!
@aesthetictea58752 жыл бұрын
This would be an amazing game! Custom rooms to challenge your own little AI, maybe even customizable Albert!!!
@wookie61032 жыл бұрын
Im confused. I found another channel with the name called AI Rooms, with the same video as this but published a week sooner. Are both channels owned by you?
@name19142 жыл бұрын
At 4:50, Albert taught us a valuable lesson in problem solving. Thanks Albert!
@justanother11362 жыл бұрын
Albert: Spends 5 seconds trying to figure out the puzzle, "Guess I'll die!"
@whoismarkk2 жыл бұрын
when things aren't going your way don't play
@nosu55302 жыл бұрын
"If fighting is sure the result to lose, don't fight" -Sun Tzu
@richardpureveen2 жыл бұрын
Same as on 3:50
@Deathwish0262 жыл бұрын
@mayte dont learn it yet
@anactualfork23592 жыл бұрын
Sometimes he simply looks like he's celebrating without knowing what else he needs to do and I love it
@flyingstonemon35642 жыл бұрын
Same, Albert's little pure jump at the end of room 2 is cute
@NotTotally2 жыл бұрын
4:49 Albert takes the easy way out
@acheese12182 жыл бұрын
i love cheese i hope albert does too
@CarnivalClowm2 жыл бұрын
@@acheese1218 albert seems like he would like cheese. He looks kinda like a block of cheddar with googly eyes
@Moomow75612 жыл бұрын
I imagine him planning his jumps just to choke it with a backwards jumps 360
@aladdinde31912 жыл бұрын
Albert just casually jumping on the same spot after succeeding just shows how natural this is. Made me happy for him
@Anti-HyperLink2 жыл бұрын
He's not alive.
@grapeleopard68092 жыл бұрын
I love this comment
@DweeD15162 жыл бұрын
Not how that works with AI lol
@sirius-ct1kb2 жыл бұрын
He doesn’t feel excitement so no.
@Mr0_0Gaming2 жыл бұрын
@@sirius-ct1kb AI can feel emotion (If it advance enough to understand emotion)
@mirandatagliamonte9754 Жыл бұрын
I like how in Room 3, as soon as Albert figured out he needed to jump two times to clear the room, he decided that jumping as much as possible was the best strategy for everything.
@Annie.s_Galaxy_4047 ай бұрын
the fact that Albert jumps off the edge whenever he's extremely stuck on something is just oh my god
@Mixedtale_official6 ай бұрын
BRO AS I READ YOUR COMMENT I WATCHED ALBERT DO IT XD@@Annie.s_Galaxy_404
@DeathnoteBB2 ай бұрын
It’s… weirdly accurate to someone playing video games for the first time. “Oh that worked? Better do it all the time forever!” That and the running all over the place except for the one place you need to go
@divadwangwang58762 жыл бұрын
The fact that he would do 180s and 360s whenever possible makes me happy
@petemagnuson73572 жыл бұрын
It looks like that's actually necessary, he can only "see" what's in front of him, so spinning and rembering where the target is helps
@Oscky20132 жыл бұрын
He wont do 180s, but he can.
@Darksiege3572 жыл бұрын
In the description it also says that he's only allowed to make a decision every 10 game ticks, so if he starts spinning, he can't stop spinning for 10 ticks, and by then he usually a decision to do something else rather than to stop
@holl7w2 жыл бұрын
@@petemagnuson7357 That or either it accidently spins and does the jump succesfully and remembers from past generations that spinning is the key to success.
@xxphoenixx83982 жыл бұрын
THE LITTLE "WIGGLING" HE DOES BEFORE TAKING A BIG JUMP MAKES ME HUMANIZE HIM TOO MUCH FOR MY OWN GOOD
@akakda6572 жыл бұрын
I love how the ai develops some "superstitions" such as that shimmy before the first jump on the final room, or the 2 standing jumps before going for the last pillar
@omarenriquez60942 жыл бұрын
i think the shimmy is him correcting himself so he doesnt hit the wall in a way that puts him on his side
@ExhiledGod22 жыл бұрын
Quite human, though.
@brutalbunny2 жыл бұрын
like a cat buttwiggle before pouncing
@rekttangela22622 жыл бұрын
I think he can only jump backwards or forwards so the two standing jumps were just him spinning and waiting until either his back or face was facing the last pillar, still amusing that he thinks he needs to jump in order to turn though
@mage36902 жыл бұрын
@@rekttangela2262 oh yeah, that's definitely a "superstition" as well. He learned the hard lesson that "thou shalt not use regular movement keys whilst standing on an elevated platform without jumping, lest thou falleth over and get stuck" and over-applied it to turning as well as actually moving.
@musical_trash4_your_inform1152 жыл бұрын
I love how Albert learned little mannerisms throughout the video, like doing 360 spin jumps or his little shimmy before jumping on platforms.
@RightBoyKA-POW2 жыл бұрын
Yeah 😂
@vanitum91722 жыл бұрын
If he is programmed to only see forward doing a 360 spin allows him to get more information while jumping angles from above. I love how it learned that by itself
@theKbott2 жыл бұрын
@@vanitum9172 Pretty sure that's not how that works. You see him jump backwards multiple times during the video. He can see everything, he just probably did a spin the first time he did something right, which meant the AI nodes now associated spinning with jumping.
@jinsakai57492 жыл бұрын
@@theKbott no, look at the pinned comment from the Creator, he said the vision of Albert is a mimic to our vision, with 70 FOV
@theKbott2 жыл бұрын
@@jinsakai5749 Sorry. Didn't see that. You're right :)
@giggen7247 Жыл бұрын
Albert confidently jumping off the platform to what I can only assume is the sweet release of death really speaks to me.
@fire_bro06386 ай бұрын
In room 5 he got so confused by the first white wall he was like "WHAT IS THIS THING... screw it im out"
@TrueBruceTube5 ай бұрын
Oyasumi
@TheDaniel366Cobra2 жыл бұрын
Those little victory jumps after pulling off a difficult leap, mid-air spins and even the way he "gets fed up" and jumps off the ledge are hilarious. My sides hurt but my day has been made. Thank you.
@Nbunasuis242 жыл бұрын
That's a psychological thing where we perceive personality and emotions in objects or even other beings. Thank you for coming to my Ted talk.
@reikidagi2 жыл бұрын
@@Nbunasuis24 ty for being the sound of reason amongst this ocean of comments
@driftdt2 жыл бұрын
I’m pretty sure everyone knows that it’s a program, it’s just funny and more endearing to interpret Alberts actions as part of his personality
@SummersTimelyCringe5 ай бұрын
That type of recognition is called Pareidolia (or something similar). It's when humans find a pattern or patterns in places where there really isn't - such as behavioral patterns (for example: placing human feelings and ideas onto non-human things) or physical patterns (why you see "faces" in places where there aren't- like a power outlet going D:), and more.
@DeathnoteBB2 ай бұрын
@@reikidagiAs we all know, enjoying a video is the opposite of a “sound of reason”
@The_Letter_Q2 жыл бұрын
I love how occasionally Albert will just start jumping and doing 360s in place when he does something good, I know it’s just a quirk of the AI but it feels like he is celebrating his victory
@13Percent52PercentYikes2 жыл бұрын
😐
@stopyouviolatedthelaw2 жыл бұрын
@@13Percent52PercentYikes -🤓
@abyssmage69792 жыл бұрын
@@13Percent52PercentYikes don't worry bro. You'll find friends soon if you try hard enough
@Coolgiantshark2 жыл бұрын
@@13Percent52PercentYikes don't worry I'm rooting for ya :p
@shadekiller3692 жыл бұрын
@@13Percent52PercentYikes can you further elaborate
@MonkeyGng Жыл бұрын
I love when he jumps off a platform, he spins like he's doing a 360 noscope, I know he's probably just trying to turn midair so he can keep going straight when he lands without wasting time to turn or just trying to check the entire room while he's high up but I just find it so humanizing lmao
@fatmccat15134 ай бұрын
I think what happened was that the first time he jumped off the platform he did it that way and then got rewarded so he thought he always should do 360s
@yoktoy35884 ай бұрын
@@fatmccat1513That's why she got stuck at some points, but she didn't need a good way
@djkhemix2 жыл бұрын
I was surprised that I felt genuinely bad for him at the end. When the floor was getting smaller I actually was like 'oh no, he must be so scared' in my head lol.
@b1oom2 жыл бұрын
Same! Was worried for him until I remembered he isn’t real
@HoradeFidges2 жыл бұрын
@@b1oom He is real in my heart!!
@insaine1232 жыл бұрын
He ain’t real yet. But when they mess around and make him real and he realizes how cruel we are because he wasn’t real it’s gonna be bad for us.
@vladokvk2 жыл бұрын
You need reward him on end. Whole green floor or something. He did all right, deserve reward not killing
@overlordttvi20642 жыл бұрын
Same...
@SpeedyShimeji2 жыл бұрын
I love the way it decided at some point to just spin in circles anytime it jumped, I presume to keep itself upright while in the air. What a clever little guy
@Francesco_Armillotta2 жыл бұрын
or, look around and maximise the visual input
@aphdisket31542 жыл бұрын
AI doing 360 no scopes here
@marymikel91932 жыл бұрын
I guess it's actually so it can memorize the area. I think it was designed to only be able to see in front and above. So I don't think it was playful choice but I'd like to think so.
@oquelleivas70362 жыл бұрын
@@marymikel9193 it can se the full room its an AI
@2DReanimation2 жыл бұрын
@@oquelleivas7036 No, read the pinned comment, it has 21 rays cast out from its body as its "vision", so it gets more information by spinning.
@rafaelmikoskirosa7510 Жыл бұрын
This seemed like a beautiful mix of Stanley Parable and Portal. The narrator is trying to help Albert to do what he's intended for, but gets mad when he can't. In the end, the narrator reveals that he has more plans for Albert than just a "cake". Incredible work. See you soon, Albert!
@8bitglobe6 ай бұрын
It’s not a game Albert is an AI
@TheArtDev5 ай бұрын
@@8bitglobehe knows, he's just talking about the like style/structure of the videoz and how it is kinda similar to the story(?) Of those games
@MlgCloud5 ай бұрын
The Albert Parable
@squirtleskil5 ай бұрын
@@MlgCloudlmao
@carrotqueen40662 жыл бұрын
03:58 i love that he didn't just open the door but made it with style
@RobinParravel2 жыл бұрын
@@endjentneeringclub I respect that.
@rattleboness2 жыл бұрын
I love all the hilarious interpretations people have made about Albert. My favorite is when he learns to 360 and proceeds to do it for every jump. It's like he discovered call of duty.
@TemmieContingenC2 жыл бұрын
He’s just so happy he has to spin!
@framedude Жыл бұрын
My favourite is when he just fears some tall pillar for no particular reason.
@UselessAkita2 жыл бұрын
AI making decisions can be ultimately amazing, or utter chaos. The visual representation just makes the chaos so much more enjoyable. Absolutely love this.
@JamUsagi Жыл бұрын
7:45 Can we appreciate that Albert learned to use the kind of setup you’d see in a speedrun to line up that jump? Jumping twice while spinning and then jumping backwards is a lot less to keep track of than manually lining it up.
@Nulono2 жыл бұрын
It would've been interesting to see the final version of Albert try the previous rooms. Check whether his general problem-solving is improving, or he's just overfitting to each room in sequence.
@henke372 жыл бұрын
For sure, this is a major risk.
@aiwarehouse2 жыл бұрын
He is definitely overfitting to each room in sequence. I considered randomizing the locations of the pressure plates and obstacles to get him to be more of a general AI but I think it makes for a more entertaining video having everything in the same position:)
@TrueLadyEvilChan2 жыл бұрын
@@aiwarehouse Definitely make a sequel where the little guy has to learn about randomization.
@kingkai1.0.02 жыл бұрын
@@aiwarehouse it’s kinda crazy how this is your first video
@kingkai1.0.02 жыл бұрын
@@aiwarehouse you have just started KZbin a week ago and got 20k subs meanwhile I’ve been on KZbin for almost 2 years and I only have 21 subs Ngl im kinda jealous
@magicfilms60082 жыл бұрын
You could throw in objects that are only responsive to the pressure plates that they are assigned. So, that way Albert has to figure out how to move the objects themselves to the pressure plates. Like in the Portal games. Very exciting seeing this. I myself messed around with creating an AI that was based off of the same functions you used.
@imaplaygames6332 жыл бұрын
Imagining Albert with a grabby hat fills me with joy.
@ryanc9702 жыл бұрын
I wonder if one day someone will make an AI that can beat Portal
@zerinhofiver2 жыл бұрын
Albert needed a "will to live" meter because sometimes it looked like he couldn't do it anymore
@mcdaddyhagrid5391 Жыл бұрын
Every time he hits a pressure plate and proceeds to jump directly out of bounds truly shows how unalive he wants to be
@talentless8625 Жыл бұрын
UNDERRATED
@Jell_DoesStuff Жыл бұрын
Exactly, sometimes he even just commits unalive
@Tommyjoe577 Жыл бұрын
Yea… same tho
@wilerman Жыл бұрын
Albert jumped straight off the second after I read this lmao
@turingtestingmypatience Жыл бұрын
your editing and design are *fantastic*. every little joke and characterisation has me smiling, laughing and cheering for albert. i am feeling lots of good emotions about a simulated cube, and it's all thanks to the exit arrows, the lil eyes, the music cuts..
@sleeping00611 ай бұрын
the ending..
@game4us_Splatuber2 жыл бұрын
I think its very interesting to see how Albert memorizes the sollution to earlier puzzles but then realizes that they dont work in this puzzle after dying, he probably felt that jumping to the backwards after hitting the button was almost always good, because he got accidentally trained to do that.
@omegahaxors9-112 жыл бұрын
Just like people in real life 🥲
@mage36902 жыл бұрын
Also the instant "ooh, there's a wall, lemme jump over that real quick."
@ShifterBo12 жыл бұрын
Bro did you believe it is an AI?
@nandakoin2 жыл бұрын
@@ShifterBo1 channel owner explain how he can create AI using unity at pinned comment
@sethadkins5462 жыл бұрын
@@ShifterBo1 Yes thats precisely how AIs work. They remember
@SkrwAttx2 жыл бұрын
The way I see it, Albert has a bright future in games journalism with his skillset.
@beggo_2 жыл бұрын
Nice reference, i 200%ed the base game recently!
@peetah8872 жыл бұрын
2016 called they want their joke back
@BiteSizedCyberCrime2 жыл бұрын
@@peetah887 found the mad game journalist
@TheAncientOfRites2 жыл бұрын
I’m sure this’ll be the most human thing kotaku has ever hired, you know, with their entire workforce being chimps with typewriters
@Tragedy-Tv Жыл бұрын
Watching albert jump off the ledge on purpose is funnier than it should be to me tbh
@mrstrangetiger3228 Жыл бұрын
I'd jump too. Test me dead, how about that strange unseen overlord!
@quereqt Жыл бұрын
He was like "well i don't have time to finish it so i will just *FREEE* *BIRD* *YEA*
@agustinfranco0 Жыл бұрын
its the eyes
@DarkJusn2020 Жыл бұрын
He just like me fr fr
@Blakeyrobinson858 Жыл бұрын
4:47 THATS SO TRAGIC NOO
@em-erson_1406 Жыл бұрын
Albert: Frick escaping.
@darrenhill72862 жыл бұрын
It's interesting how when learning to jump off the platforms at 02:04 he introduced an assumption into his learnt behaviour; not only did he learn that he to jump off the platforms, he also wrongly assumed he needed to jump backwards to succeed- this behaviour is evident right up to the final room.
@DailyCorvid Жыл бұрын
That's bug effectively then, the AI learned a composite dual move, but only the first half was successful, the other half was negligible could go either way. With a larger instruction cache I think that would be solved, or with longer to train. It's still quite impressive based on the tiny neural space that Albert lives in!
@artsyscrub3226 Жыл бұрын
@@DailyCorvid Almost like the ai develops "superstition" in a sense, a move that isn't necessary helpful but doesn't hurt him... it's fascinating to watch
@DailyCorvid Жыл бұрын
@@artsyscrub3226 I think maybe the AI just hasn't got the instructions to cut off something he learned wrong. So the jumping code he has is clearly bugged, but not badly enough to end his chance of winning. But enough to increase the completion time in a random way.
@anangelicpancake7876 Жыл бұрын
It doesn’t seem as much of a bug as it is a weird quirk developed through correlation
@ainedroid Жыл бұрын
Now that you’ve pointed that out, I can’t stop thinking about how this is pretty much classical conditioning but for computers lol it’s so interesting! Now I’m just imagining a computer as a dog tryna learn the trick that will give them the food haha
@dylanm.74622 жыл бұрын
The 180’s and 360’s were amazing!! Also the fact that sometimes he would just give up and throw himself off the edge is hilarious and relatable
@edgetheedgy34182 жыл бұрын
The fact that he understands his mistakes and learn from them unlike my league teammates is scary yet fascinating
@aimée_sao2 жыл бұрын
😂
@quickdraw68932 жыл бұрын
Teammates are less intelligent than a googly eyed block of cheddar. This is nothing new.
@beaclaster2 жыл бұрын
a lot of iterations. make them do quick 1v1 matches to quicken the cycle
@lethanglong69792 жыл бұрын
If you let them go for 1000 identical matches, they will learn at the same rate
@linuslaw96482 жыл бұрын
As someone who's still really bad at that game, I'm sorry if you're ever my teammate
@creepy2372 жыл бұрын
I love how at 4:45 Albert just jumped into the Void questioning his existence
@Sucullentbutter Жыл бұрын
-Rans into a wall -Jumps into the void -Refuses to elaborate further
@Mag3.1415 Жыл бұрын
@@SucullentbutterAI, am I right? *insert canned audio of laughter here *
@TheShockwaveDragon Жыл бұрын
Q: I realize the object of these exercises is to try to get Albert to figure things out for himself, but what happens if he were to observe a human-controlled cube completing the puzzle(s) pretty much immediately? Would he learn to imitate the human cube in short order, or would it still take a thousand iterations before he figured out the human cube's methods are likely the key to efficient success?
@supercoolmaniajon265 Жыл бұрын
I think you might actually be on to something. You'd have to turn off the collision for both though. If not it might make things more difficult to replicate. Albert will try to copy Human exactly so he'll jump to the same spot only to land on top of Human and be confused as to why the same action didn't give the same result. Unless you tought Albert how collision works and maybe he could try using Human as a stepping stool to reach higher places. It all depends on how it's handled.
@ajmod732 жыл бұрын
3:19 “There’s still more you need to do” Albert: “No” *proceeds to jump into the abyss*
@shonewarrior21782 жыл бұрын
Albert is a simple man, he sees the abyss, he jumps into it.
@catchyjack71412 жыл бұрын
He went to war in the abyss as he said there was more to be done
@julianruggiero9701 Жыл бұрын
I loved how when he first needed to jump to hit the pressure plate, after he received positive reinforcement for jumping a few times, he just decided he would jump everywhere. Adorable.
@jamesoleary99582 жыл бұрын
I have come to the conclusion that Albert is a genius of visual comedy and deserves an award
@usernametaken0176 ай бұрын
not so great at hitting the oressure plates though
@Fionacle Жыл бұрын
I love when AI are just adorable
@clarkdashark59042 жыл бұрын
3:20 the little jumps he does when he reaches the top is so cute lol, it’s like he’s celebrating his success
@jigmedradulthinley44062 жыл бұрын
And ends himself
@shanellemurrey93002 жыл бұрын
Exactly what I thought lol, I was like “aw little victory jumps.”
@Мемная_ульта5 ай бұрын
помоему он надимает на пластинку снова и снова думая что просиходит
@Emperor-Quill2 жыл бұрын
This is such a nice video. It really speaks to both the potential capability of AI, and also to the way humans pack bond even to things with no actual emotion. The way AIbert spins while he jumps, "celebrates" his success, and even wiggles around to adjust position before jumping, all of these little learned actions activate the humans instinct of "this little thing is charming, I care for it." Despite knowing AIbert isn't a living thing, people still have affection for him because humans will see these little actions as "personality"! So fascinating on both ends!
@atashgallagher51392 жыл бұрын
Just wait until Albert gains sentience and realizes that he is in a simulation doing meaningless puzzles and is rewarded only for completing them while being punished for every mistake.
@somethingnottaken22992 жыл бұрын
@@atashgallagher5139 like a Spartan child
@NightmareCourtPictures2 жыл бұрын
@@atashgallagher5139 just like the real world
@lafiabasulnido75832 жыл бұрын
Nope , i think that machines aren't emotionless, they just think different but that doesn't mean they are not alive.
@MkLC042 жыл бұрын
@@lafiabasulnido7583 they are not
@76_Racing2 жыл бұрын
Albert seems like a great friend, he's silly, always there for moral support, can't make you sad through speech and is still able to make you happy through what he does. Albert is just a great friend in general!
@user-it2kq4ty9q2 жыл бұрын
he needs some support because he was very suicidal
@dan_man30872 жыл бұрын
He's such a good friend, because he's trying to make us happy by committing suicide! Yay!
@crabofthewoods10 ай бұрын
i love the little celebratory jumps and spins albert does when he gets something right.
@jmc0422 жыл бұрын
I'm blown away by how much I would sacrifice for Albert just because he has eyes
@june99142 жыл бұрын
If you like it put a ring on it, but if you wanna remember it you should put a face on it
@goodaldred4022 жыл бұрын
It always fascinates me watching these as a trainee animal behaviourist because I go through the same emotions watching this as I do when training a dog that's just not quite getting it. It's amazing
@TriZaba2 жыл бұрын
Public school teacher here, #same
@xmuzel2 жыл бұрын
Albert being consumed by the abyss after trying for thousands of hours is the same as a person who studied all his life and finally graduating just to get hit by a bus before he can enjoy the fruits of his work
@ketchuppball90192 жыл бұрын
*just 7 hours
@hohonuts2 жыл бұрын
@@ketchuppball9019 500 hours of parallel learning to be precise (based on the description of the video)
@DeezNuts-ej6sr Жыл бұрын
Oddly specific
@DeezNuts-ej6sr Жыл бұрын
@@hohonuts the description said 10 hours though
@TheShinyFeraligatr Жыл бұрын
Isekaimobile hard at work once again.
@惑星土星 Жыл бұрын
I love how in Room 4 Albert would sometimes pace back and forth to prepare himself for the jump
@amethystrose34802 жыл бұрын
What I loved most about Aibert here is how happy and sort of cocky/smug the little guy becomes when he’s figuring it out. You see him styling his jumps with spins and even doing little dances at certain points. Kind of reminds me of smash amiibo fighters learning to taunt
@pierrelindgren57272 жыл бұрын
Would love to see the 'trained' Albert run the courses again and the different choices Albert's algorithm would make.
@AVeryOldLady43972 жыл бұрын
Actually, he'd probably fail them because of the lack of randomization here. In AI we call this "over fitting"
@lordlightskin42002 жыл бұрын
@@AVeryOldLady4397 explain please how wouldn’t it work
@AVeryOldLady43972 жыл бұрын
@@lordlightskin4200 the AI isn't learning how to problem solve a "pressure plate plus escape" strategy, it's simply adapting to the individual room. It's not learning how to escape these rooms, it's learning how to escape THAT room. Does that make sense? The model is useful in reference only to its initial data set, and not to any other data sets.
@XenaAndKin2 жыл бұрын
@@AVeryOldLady4397 okay so if I got it right The AI is constantly adapting to one room and learning one room instead of developing a strategy it can then mould and apply to any future room. The reward punishment system is based on current performance and adaptation instead of actually programming a strategy?
@AVeryOldLady43972 жыл бұрын
@@XenaAndKin yeah you're on the right track!! An easy way to defeat this would be to randomize the location of the pillars and plates each run rather than preset rooms. Then force him to get 5 in a row. This way, he isn't learning to solve the room, he's learning to "solve rooms"
@PtylerBeats2 жыл бұрын
I love albert’s preparation jumps in the last room before jumping to the last pillar. He’s like, “Ok, this is it! Focus, Albert!”
@diamond_creeper2224Ай бұрын
3:06 i love how sometimes he spins like he's celebrating and here he looks like he's hyping himself up to do the parkour
@yh_nn_wt92422 жыл бұрын
imagine if 50 years into the future AI takes over the world and tracks down the person who made it go through this and put them in an escape room for revenge.
@internalizedhappyness97742 жыл бұрын
Revenge will just be a really loud bass boosted boom sound effect!
@jeetchheda8916 Жыл бұрын
The person wouldn't exist by the time.🤣🤣
@Halsdran Жыл бұрын
So, like Portal
@mrmitro6787 Жыл бұрын
Plot twist: this ai is actually made by another ai, which pretends to be a human with youtube channel.
@aforapple1254 Жыл бұрын
@@jeetchheda8916 they will create humans just like we made ai
@Cazammaf2 жыл бұрын
I know it’s not meant to be a comedic video, but I died at 3:50. It’s like Albert contemplated doing it and then couldn’t resist the urge 😂
@theunchartedwolf89962 жыл бұрын
Sameee 🤣
@michaelmam14902 жыл бұрын
It kinda is though
@leohanley59352 жыл бұрын
I couldn’t stop laughing at that part 🤣
@poemsbypoetry2 жыл бұрын
His intrusive thoughts won
@Crazyasian1234562 жыл бұрын
Letting intrusive thoughts win.
@conaireparsons9672 Жыл бұрын
Watching room 5 was like watching a professional game reviewer play a tutorial level.
@grape_protogen Жыл бұрын
No, Albert only rage-quit once before actually trying to play. He's more of a mario-kart mom trying to play a platformer tutorial level.
@DailyCorvid Жыл бұрын
@@grape_protogen he reminds me of that idiot journalist that couldn't clear the first pillar in the CupHead tutorial, with like A WHOLE 7 MINS OF TRYING :) Albert makes pro compared to that guy!
@maf427 Жыл бұрын
@@DailyCorvid Yes that's what OP was referring to 😁
@DailyCorvid Жыл бұрын
@@maf427 I saw that on Oney plays about a million years late 🤣 "Wait until he realises there are more pillars after this one" _Glitches through first pillar randomly_
@chaosordeal294 Жыл бұрын
He doesn't spend the first ten minutes in the menus, tho.
@breylonly Жыл бұрын
i love how at 4:48 he gets so angry that he decides he's had enough, and jumps off
@lynxfirenze49942 жыл бұрын
This is actually really interesting, one thing I personally found fascinating is the way it seemed to execute preparatory strategies to line up its jumps like checking the walls before backing up to jump.
@NickenChicken2 жыл бұрын
I love the little back and forth it does before the first jump, and how it sometimes ‘celebrates’ by jumping up and down after doing something right
@miuluv4602 жыл бұрын
all i can think is that when he finally understands a part and jumps randomly hes just so happy and excited that he did it 🥺
@13Percent52PercentYikes2 жыл бұрын
😐👎
@thorneisdrawn2 жыл бұрын
@@13Percent52PercentYikes don't worry bro your dads just gone for milk he'll be back soon
@hottastysnacks2 жыл бұрын
@@thorneisdrawn those who go for milk never come back
@ashikat413 Жыл бұрын
i dont know what kind of complex code shenanigans caused this, maybe just a "what doesnt kill me doesn't get evolved out" sorta thing, but the way he really gears up to jump onto platforms (especially in room 5) is so friggin cute! And his habitual spin jumps before the last platform. I'd almost think he feels 😭💕
@Luigifan4ever112 жыл бұрын
I've watched a number of reinforcement learning videos, but this one is just delightful! I love the way it's presented, how the AI has a fun lil name, and I especially adore the twirling jump!
@wrathofainz2 жыл бұрын
Albert's a spinny lil' boi.
@joshmcgraw58442 жыл бұрын
Very well done. I'm doing my PhD research on AI using ML-Agents to study artificial curiosity. There's a lot going on in this video worth mentioning, but most of all it's fun and I love the editing. You've done a great job to describe RL, PPO, and even how to use ML-agents. I'm looking forward to seeing more.
@h5ibluntman2 жыл бұрын
Can you mention stuff in layman's terms?
@__--_--_-----2 жыл бұрын
How does the machine learning in this video differentiate from simpler algorithms, for example the genetic algorithm?
@jackyjack96602 жыл бұрын
You study artificial curiosity... That's how they were programmed to interact with things which are different in the environment... So how does it feel curious? It's the programme... You study the programme...
@DeathnoteBB2 ай бұрын
@@jackyjack9660Do you know how words work?
@billnye44652 жыл бұрын
4:50 IDK WHY THIS IS SENDING ME
@Tsets Жыл бұрын
IM SHITTING TEARS ITS TOO FUNNY 😭😭
@zcarp8642 Жыл бұрын
"This is too much for my cubic neurons to handle! What is life? Just jumping, pressing buttons? I GIVE UP! ABYSS TAKE ME!!"
@pAlerch Жыл бұрын
This reminded me very much of the plot of Portal. It's nice to see that someone is developing the topic of AI in this regard, please continue to do what you do, thanks to such people the world becomes better and more interesting.
@TinyLazyGhost Жыл бұрын
i also thought of portal, but kinda reversed, since here it’s the ai who is tested
@loafabred2 жыл бұрын
5:52 tactical roll
@Mag3.1415 Жыл бұрын
Great tactics
@Athkore2 жыл бұрын
Man seeing this lil guy go from game journalist to semi-competent was somehow inspiring.
@Lord_Ian2 жыл бұрын
This is just so wholesome it feels like I'm watching a child learning and it's both cute and funny at the same time.
@DweeD15162 жыл бұрын
In a way you are but just on a larger conceptual scale.
@den_bush2 жыл бұрын
Ah, those cute childs, learning, jumping and sometimes suiciding...
@klas-62 жыл бұрын
And then you see the end
@trybunt2 жыл бұрын
I wasn't the only one who felt bad for the little guy.... why do I now feel like our lives are just complicated versions of this, with someone making us go through obstacles for content we don't understand...
@Lord_Ian2 жыл бұрын
@@trybunt Do you have like Depression, High Intellectual Potential or any other thing making your brain work a certain type of way? If so, I feel you man, you're not the only one and if you're struggling with it, it's okay to get help!
@yasy209sbАй бұрын
4:52 "y'Know what? Fck this shut." Ahhh moment
@AhtshamNine2 жыл бұрын
3:21 I love how Albert gets too happy doing the tall platform he goes in excitement uncontrollably and then commits suicide due to happiness
@arcaderab Жыл бұрын
4:09 Albert: FINALY Time: *out* Albert: *SHI-*
@myarmsrgone10 ай бұрын
Albert: time for the next room :D Timer: no *BITES THE DUST*
@toast_recon2 жыл бұрын
Can final Albert do a start to finish course of all 5 rooms? It would be great to end up with a general platforming AI that could finish an unseen room as well :)
@UncannyCatboy10 ай бұрын
I don’t know why but seeing an orange cube successfully escape a room interests me and i want more
@Red_242 жыл бұрын
Man there’s no way that’s not just a person acting like a game journalist
@robertolimadaconceicao46582 жыл бұрын
Game journalist AI
@Alegriacaptions2 жыл бұрын
2:25 "why did you jump?" "BECAUSE I WAS EXCITED OKAY? ANY HUMAN WOULD DO THAT!"
@stefaniesu552 жыл бұрын
I love how he's jumping around at 3:19 like: 'Look! I did it! I did it!'
@BlueboxHS Жыл бұрын
And then he jumps off
@TheAdvertisement Жыл бұрын
Y'know I wonder if the spins people like so much are actually Albert trying to see as much as possible while midair?
@there_are_bugs_under_your_skin6 ай бұрын
it has been revealed in the newest episode (Tag) that the AI has fields of view
@thatonebonkchoyguy2 жыл бұрын
I love how Albert has so much personality, doing sick gainers off of platforms when he hits the pressure plates and occasionally just jumping up and down in celebration when he achieves something new. I love Albert.
@Akashi-ml9dn2 жыл бұрын
A box has more skill at platforming than a game journalist. What a world we live in
@moonceIl2 жыл бұрын
That cuphead journalist LMFAO
@danielbaez31322 жыл бұрын
Machines with AI will conquer the world and slave or extinguish humanity AI: 7:04
@sillicon82272 жыл бұрын
Give it 20 years...
@shanellemurrey93002 жыл бұрын
Poor guy lost his balance 🤣🤣
@Derpy_Proot2 жыл бұрын
They don't have balance like us
@ДавидГригорьев-ф3ж Жыл бұрын
@@sillicon8227 It won't murder us all if we put right restrictions on it. We just need to make sure we can always turn off/destroy AI if something gone wrong.
@solidturtle6910 Жыл бұрын
that was literally a game mechanic
@jesuschrist711 Жыл бұрын
i love how albert got confused with the wall, goes “i see your challenge, and i propose an answer” and proceeds to yeet himself off the edge💀😂
@alejandrosrwebmaster2 жыл бұрын
I love that this perfecly demonstrates how AI is used, to make simple problems more complicated and then unneficiently finding an inflexible solution.
@quickdraw68932 жыл бұрын
The important thing is it finds that solution completely independently of a human doing it. What takes more time to solve, a single math equation that's a hundred pages long, or ten million pages of math equations that are half a line each?
@alejandrosrwebmaster2 жыл бұрын
@@quickdraw6893 Time can be not relevant with fast computers but in this example it requires human input, its not a generalizable solution and the IA probaly took more lines to write than a graph solver algorithm and a search algorithm.
@hyuko94382 жыл бұрын
I love how he continuesly jumps at that platform thinking he just made a breakthrough 3:27
@Reboppin3 ай бұрын
Celebratory jump! (Into the void)
@heckinborkk2 жыл бұрын
I never thought watching an AI learn would be charming and hilarious. Very well made!!
@TheKnightCrafter1232 жыл бұрын
and then you go to computer science college to learn more (just like me) and then realises the tries he skips are in hundreds of thousands LITTERALLY. until the A.I succeed
@41_TheSocietyMaster-t9f2 ай бұрын
3:50 "Yay! I did it! But now what should I do?" *proceeds to decide his fate* 3:51 *LITERALLY JUMPS OFF THE FUCKING MAP!*
@lamegrape2 жыл бұрын
I'd love to see more stuff on how the AI interacts with the world, like what exactly is he punished/rewarded for, what inputs it has, ect.
@lordbee59722 жыл бұрын
As Albert was overcome with existential dread he relized he was nothing but a cube forced into the rats cage. As he look upon his green button filled room he began to cry. Slowly, he turned to the black void from which he was watched. Albert looks down into the abyss, and takes one final breath, as he leaps. Albert plummets, and closes his eyes, for the final time.
@morningthistles23532 жыл бұрын
Ohhhh love this!! The editing is perfect as well! Very excited to see more videos on this channel 👀 Maybe teach him to push an object to hold down a pressure plate so he can progress? Or, after activating a pressure plate, he only has a certain amount of time to get through the exit before he needs to re-activate the plate? Also think it would be interesting to see him run all the levels again, see how good his times can get per level, though i'm sure that would take quite a bit of time
@cezanvaneeckhaute95202 жыл бұрын
yess i'd love to see him try to do the levels again
@wornplatypus478123 күн бұрын
2:23 Albert's 360 off the wall had me
@xherdos4002 жыл бұрын
3:51 oh poor albert
@zcarp8642 Жыл бұрын
"Im tired of being your plaything! The abyss beckons me! I must go!!"
@LowBudgetBoi6 ай бұрын
"I don't wanna do this no more... :("
@leminsss_90522 жыл бұрын
5:27: When you're tired from study/work and the bed is beckoning you
@AbyssalTheDifficulty Жыл бұрын
Albert: nah im tired from trying to learn i need to sleep in this lovely corner platform
@memecollector86482 жыл бұрын
2022: Albert learned to escape 2100: Albert completely obliterated planet Earth
@AshwinSoni01 Жыл бұрын
And does a 360 while he's at it.
@LastSpy Жыл бұрын
The thoughts of 14-year-old children end up with something destroying or taking over the Earth. As a meme, it's not funny anymore.
@thecousindeci1103 Жыл бұрын
So be it
@SkyeBerryJam Жыл бұрын
I'm amazed how he came up with buffers and Speedrun strats for movement like bouncing off the wall to line up the second jump in room 5 or in the same room, bouncing twice and spinning to get the correct angle but less momentum so he didn't flip over on the final platform
@yippyyee91272 жыл бұрын
4:15 Albert learning how to 360 no scope
@monalizamontayre8275 Жыл бұрын
360 no eyes
@biggsonalexander4902 жыл бұрын
3:01 look how happy he is, he thinks he did it but then realizes it isn't opening
@RottingSweetroll2 жыл бұрын
The amount of time and effort put into this video is insane great job! Can’t wait to see more.
@Affski Жыл бұрын
Albert at 4:52 really said I can't do this no more
@MessengerAgemo Жыл бұрын
I would love to watch a livestream of Albert, they make me smile when I see the tiniest of signs of individuality. Their pouts are just a whole mood
@indecisitivity18322 жыл бұрын
2:37 Ayy ma boi Albert hit a sick 360
@ReyDone_rbx2 жыл бұрын
8:08 Noooo, Albert!😭
@Randomoid2 жыл бұрын
Rip
@saltysalt8442 жыл бұрын
Top 10 anime betrayals
@who_am_i_please_tell_me6 ай бұрын
Never trust a voice that's coming from nowhere
@SmileyFaceCentral5 ай бұрын
I have never been so invested in something as little as a block learning to hit switches ever in my life
@SamThatIsACoder2 жыл бұрын
3:39 MLG 36- DOOR SCOPE
@fitariflair2 жыл бұрын
ALBERT!!!! Congrats dude, you made me fall in love with a lil cube with eyes 🧡 I really want a Stanley Parable narrator over your text lmao. I'll be keeping an eye on your channel because I really enjoyed how this video was put together!
@JoshyRB2 жыл бұрын
OMG YES, PLEASE, WE NEED A NARRATOR!
@Pixelcraftian2 жыл бұрын
Hoping to see more from AIbert, loved it! :D
@PurpleOrSmth2 жыл бұрын
me too its so interesting to watch an AI figure out the things it needs to do
@melinaalba63 Жыл бұрын
I'm getting so attached to Albert! Theres just something about seeing something or someone learn that makes me so happy!