More information about how Albert and Kai were trained: Time it took to train : Room 1: 12h 30m (though I stopped the recording after Albert broke the game) Room 2: 13h 40m Room 3: 1d 20h 2m Final Battle: 6h 48m (this wasn’t shown but was needed since the agents weren’t used to seeing other teammates) We continue training on top of the previous brains, meaning by the end of the video Albert and Kai both have trained for 3 days and 5 hours 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 NOTES When I mention it took x days to train, that’s in game time, and much larger than the displays indicate since there are 200 copies training simultaneously. This is a very long comment going over more of the details of how Albert and Kai works, issues they’ve had, unexpected results etc. THE BASICS: Albert and Kai were trained using reinforcement learning, meaning they were rewarded for doing things correctly and punished for doing them incorrectly (the reward is just increasing their score, and the punishment is decreasing it). After they finish each attempt, the actions they took are analyzed and the weights in their neural networks (brains) are adjusted using an algorithm called MA-POCA to try to prioritize the actions that led to the most reward. The agents start off making essentially random decisions until Kai accidentally tags Albert in the first room and is rewarded, then, as mentioned above, the weights in his neural network brain are adjusted in order to try to replicate that reward (it wasn’t this simple for this video since we use self-play to train both agents at the same time, more on that later). This leads to Kai learning that tagging Albert is good, and since Albert is punished when he’s tagged, it also leads to Albert learning that getting tagged by Kai isn’t good. This process continues through 10s of millions of steps until one of the agents consistently loses, or the agents are able to counter each other well enough to where it’s a draw. REWARD FUNCTION: Albert and Kai are given two types of rewards, group rewards and individual rewards. When Albert gets tagged he’s punished by getting a -1 group reward and Kai is rewarded by getting a +1 group reward and vice versa, encouraging Kai to tag Albert, and Albert to avoid being tagged by Kai. Additionally, Albert is given an individual reward of 0.001 for each frame he’s alive (0.6 total in a room lasting 10s), and Kai -0.001, to encourage Kai to try to tag Albert as quickly as possible. When we introduce the grabbable cubes we also give Albert an individual reward of +1 the first time he picks up the cube to make sure Albert actually starts using the cube (since without this, the rewards were too infrequent for Albert to learn to use it effectively). BRAIN: Albert and Kai’s brains are neural networks with 4 layers each (one input layer, 2 hidden layers and one output layer). The agents collect information about the scene through direct values and raycasts. Every 5 frames they’re fed data about their position in the room, the opponent’s position, velocity, direction etc., and they also collect information through raycasts (a simplified version of eyes). The agent's eyes (raycasts) can differentiate between walls, ground, moveableObjects and Kai/Albert. The agents' brains (neural networks) are given the data the agents collect from direct values and raycasts and use them to predict 4 numbers for the respective agent which control how that agent moves. An example of an output of one of the neural networks is: [1, 2, 0, 1], this would be interpreted as [1=move forward, 2=turn right, 0=don’t jump, 1=try to grab], so the agent being controlled by this neural network would try to move forward while turning right and grabbing. The fact that we have two agents training simultaneously complicates things a bit, normally we’re able just update the agents brains every x steps, but if we did that for both brains at the same time then they would struggle developing multiple strategies, since reinforcement learning tends to be best at finding a single solution, that would lead to the winner dominating and the loser stuck doing the same strategy over and over. The way we tackle this issue is by using something called self-play. Since we use self-play, we technically only train one agent at a time, and swap which is being trained every 100k steps. When we’re training Albert, we use a recent model of Kai’s brain as his opponent, and to avoid there only being one strategy, we store 10 recent brains to use as opponents, swapping them out every couple thousand steps so that Albert learns to beat all of them and not just one. This results in a much more general AI that’s hard to exploit. UNEXPECTED BEHAVIORS: In room 1 Albert manages to break out of the room by exploiting a small hole in the hitbox near the top of the room, which was there because I didn’t make the hitboxes on the walls tall enough. Though Albert used it to escape, I’m not convinced he actually would learn to do it consistently. The challenge with this video is that it can be difficult to interpret the agent’s behaviors; Albert could be making certain unexpected moves as a way to exploit Kai’s poorly trained brain to get him to make bad moves, or Albert could just be making these unexpected moves because he hasn't trained enough. Albert was able to find the hole a few times, however he wasn’t able to do it consistently, this could be from either him not training long enough, his observations not making it easy to detect when he can jump out, or Kai quickly learning to counter him getting to the display in time. In room 2 Albert also manages to glitch out of the room, and he was able to do this consistently. We made sure the cube grabbing functionality was coded as rigorously as possible, even with it automatically detaching the grab if the force exerted is too high, I couldn’t find a single way of exploiting it in testing, but Albert certainly didn’t have issues finding it. Albert also had a couple moments of throwing the cubes at Kai and spinning with the cube to throw Kai out of the room, we didn’t even consider this being a possibility before training, AI’s able to come up with some really clever solutions to problems. OTHER Thank you so much to our amazing team that helped make this video! Jonas helped with setting up the character controls, Tyler helped create the clean grabbing functionality, Catt helped edit and Andrew and Steve helped solve any issues we ran into while making the video. If you want to meet our team and talk to all of us, join our discord server!:) discord.gg/qDRtuFe5gp
In a game where the most aggressive thing you can do is a light prod or moving a foam cube, Albert clobbering Kai into a different frame of existence is pretty Gamer of him.
"It's Kai, the Blue Cube! He's loveable but he has an attitude on account of those frowny eyebrows! We hope he'll be a welcome addition to the game crew." (200 sim-hours later:) "We regret to inform you that the Blue Cube is racist now."
Quran 21:33 َAnd He is the One Who created the night and the day, and the sun and the moon each one floating (and moving) in an orbit youtube mary and jesus in the quran and mohmmad in the bible and the Torah and the scientific miracles of the quran and mohmmad in hindu scripture … according the bible that you have
(Matthew 4:1) Jesus was tempted (James 1:13) God doesn't get tempted (John 1:29) Jesus was seen (1 John 4:12) No man has ever seen God (Acts 2:22) Jesus was and is a man, sent by God (Numbers 23:19, Hosea11:9) God is not a man (Hebrews 5:8-9) Jesus had to grow and learn (Isaiah 40:28) God doesn't ever need to learn (1 Corinthians 15:3-4) Jesus dies (1 Timothy 1:17) God doesn't die (Hebrews 5:7) Jesus needed salvation (Luke 1:37) God doesn't need salvation (John 4:6) Jesus grew weary (Isaiah 40:28) God Doesn't grow weary (Mark 4:38) Jesus slept (Psalm 121:2-4) God doesn't sleep (John 5:19) Jesus isn't all powerful (Isaiah 45:5-7) God is all powerful (Mark 13:32) Jesus isn't all knowing (Isaiah 46:9) God is all knowing ................... .............
10:15 I absolutely love that four of them just instantly died cause they could not comprehend what was happening fast enough, and one just instantly kicked into life or death mode and started doing insane strategies on the fly to avoid the army of death following him
he seemed to have gotten in contact with a Kai less than a second before they all confettied, but he looked death in the face and waltzed out of the way
Very accurate observation! It appears to be the only way to survive in real life as well. The science version of this answer is that the heat death of the universe, and death of our home star, is only avoidable with some kind of way to either reverse entropy (very difficult) or to escape this universe and go to a new one (also difficult). Scientists state that they are not sure if either are possible, but that does not stop them from trying to work on the problem. The metaphysics and philosophic answer to mortality and the end of the universe is to ascend to a higher world, hence the purpose of this life is to prepare or to bring experiences and mature before we go to the next. This might actually not be completely incorrect if we look at near death experiences and events where people knew and saw things that should not have been possible. The economic answer to the tendency for profit to decrease (economies gradually slow down and asset markets become saturated) is to escape to a new market, a new frontier, or develop new technologies. Either of the above we see creatures of high intelligence searching for a way to escape mortality by ascending to a higher realm. Even the cute little boxes with eyes come to the same conclusion in their simulated world.
@@user-nu8in3ey8c "If break, fix. If fix cost same as replace, replace. If replace scary, gtfo of here." Sun Tzu said that, and so did George Washington when he tamed the first t rex.
This is actually a fairly common thing for learning algorithms to do. There was one I remember reading about which was tasked with finding landing approaches with minimal damage to the plane it was flying. Eventually it started flinging itself at the ground fast enough to overflow the damage calculator, resulting in a massive negative damage number.
Oh I just love the fun little dynamics you can see here, like Kai exploding from frustration in a corner while Albert hangs out on the ledge, Albert being an absolute MENACE to level design, Kai stomping on Albert's remains after his victory, and Albert in turn throwing cubes at him aggressively 😂 I've wondered of statistical unfairness of a game of tag in a plain environment and environment with obstacles present, there's clearly a strong connection as seen in the first two levels. But soon enough these two brought so much chaos to the scene I forgot to be analysing and just enjoyed the show. We missed you, Albert and friends!
I love how you basically reimplemented the hide and seek experiment from OpenAI and ran into the exact same problems as them with the agents abusing the simulator physics
@@siliciaveerah9327 Lol I loved discovering stuff like this back when I played Roblox. Prop flinging never gets old though, it doesn't matter what game.
ok maybe its just because of the annoyed eyebrows. I think if it wasnt for the annoyed eyebrows a lot of people wouldve rooted for Kai, probably me included
9:46 Four of them instantly died of not knowing what to do, but the last one went full sweat mode, and activated his *ULTRA INSTINCT.* He has avenged his falled comrades.
Imagine piloting a mech, but you dont know the controls, and your 'vision' is just 48 evenly spaced dots that change color based on what would be seen. You also get an electric zap if you do something wrong, but it would take a lot of trial and error to figure out what is 'wrong' and how to avoid it. Similar thing with rewards. Eventually you would figure out things like yhe time limit based on the shock and the dots resetting to the same spot each time.Thats what it's like to be Albert. Be nice to Albert
I just want to appreciate how you have framed the punishment and rewarding of a deep learning model in such a way that it’s very intuitive for a wide audience
This is actually a great example of how the rules to a competitive game will greatly influence how the competitors will play the game, even beyond what the rules intended. Since Albert gets rewarded for not being caught, but doesn’t get punished for leaving the arena, he‘ll just do that, even if it goes against the original spirit of the game. Or like how in many modern martial arts the point system introduced to establish a winner allows for effective strategies that work in the environment of the sport but would not have been feasible in the context of combat that the art was initially developed for.
My favorite genre of A.I.: No art thievery. No job thievery. Just A.I. learning how to play tag. Edit2: Obviously, the first edit didn't help, so I'm just gonna delete that. Sorry y'all. 😓
@@scoreandspore.5606it does actually bc to make AI art the AI has to take art that already exists and smash it all together to make a new piece, and it’s been proven time and time again that the creators of these art engines LOVE taking art without consent for their database. Without human art, AI would never be able to make art, and as soon as AI starts pulling art from other AIs it’ll just poison itself.
I love how human you can make AI feel/seem even with such simple mechanics and graphics. You made them especially more human with the addition of Kai with playing Tag... the subtitle text you add also helps make them feel human, like you're a human being the game announcer for these AI, narrating what they're doing to make them seem human. Also, still love the theme of having the AI names just have some way of including "AI" in normal names: "AI"bert, K"ai"
I love watching Albert just absolutely send it. Idk what it is but seeing him fly straight into space in half a second is hilarious you blink and miss him
You hear stories of someone accidentally stubbing their toe on their Roomba, and having to coddle and apologise to it. I think humans just have an affinity for Funny Little Guys.
Yeah. Anything that might to appear to be "alive" even though its completely inanimate or doesn't really have a mind of its own, we still feel the want or need to bond/apologize to these things xD probably the same way you imagined your little plushie to be sorta real
This is a type of channel who post video every 4 months but you know that the video that will come out will be a banger And this channel is the perfect example 🗿
Final test, albert did alot of impressive things that most missed. He used the boxes as a barrier and threw the boxes when a Kai is on it. Double jumps. Hides his back to a wall to no Kai can exploit his lack of back vision. Then jumping when a Kai is landing, and staying on the ground when a kai in jumping to exploit their vision, they can't see up or down, only front
Great vid showcasing the AI learning a skill, I've always enjoyed watching these. However I am more impressed with how well the sponsor ad was implemented in such a way that it felt tied into the actual content, and engaging with content-relevant examples. Keep up the great work! I'd love to learn how to program AI that learns by itself.
My co-worker showd me this a few years back. They were working with about the same learning, a tagger and an avoider. After some time they did things which he had not expect or considered at all. It was rather interesting.
@2:15 This is called 'skywalking' - it's not necessarily a hack, but those who find the holes in the world can either fall great distances or walk on the sky itself. Well done, Albert and Kai. Final battle was like watching a Ms Pac Man expert. Excellent video.
On my rewatch they throw cubes at each other to escape or Kai throws it at a wall when he can’t get Albert and when either wins they bathe in each other’s blood or completely scatter the others remains with a cube and it just seems personal when stuff like that happens in these simulations and i know they can’t feel emotions but they really seem to hate each other.
Albert learning to leave the boundaries of his world (and launch his enemy out of it) was not the plot twist I was expecting, but a fun one nonetheless!
More information about how Albert and Kai were trained:
Time it took to train :
Room 1: 12h 30m (though I stopped the recording after Albert broke the game)
Room 2: 13h 40m
Room 3: 1d 20h 2m
Final Battle: 6h 48m (this wasn’t shown but was needed since the agents weren’t used to seeing other teammates)
We continue training on top of the previous brains, meaning by the end of the video Albert and Kai both have trained for 3 days and 5 hours
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
NOTES
When I mention it took x days to train, that’s in game time, and much larger than the displays indicate since there are 200 copies training simultaneously.
This is a very long comment going over more of the details of how Albert and Kai works, issues they’ve had, unexpected results etc.
THE BASICS:
Albert and Kai were trained using reinforcement learning, meaning they were rewarded for doing things correctly and punished for doing them incorrectly (the reward is just increasing their score, and the punishment is decreasing it). After they finish each attempt, the actions they took are analyzed and the weights in their neural networks (brains) are adjusted using an algorithm called MA-POCA to try to prioritize the actions that led to the most reward. The agents start off making essentially random decisions until Kai accidentally tags Albert in the first room and is rewarded, then, as mentioned above, the weights in his neural network brain are adjusted in order to try to replicate that reward (it wasn’t this simple for this video since we use self-play to train both agents at the same time, more on that later). This leads to Kai learning that tagging Albert is good, and since Albert is punished when he’s tagged, it also leads to Albert learning that getting tagged by Kai isn’t good. This process continues through 10s of millions of steps until one of the agents consistently loses, or the agents are able to counter each other well enough to where it’s a draw.
REWARD FUNCTION:
Albert and Kai are given two types of rewards, group rewards and individual rewards. When Albert gets tagged he’s punished by getting a -1 group reward and Kai is rewarded by getting a +1 group reward and vice versa, encouraging Kai to tag Albert, and Albert to avoid being tagged by Kai. Additionally, Albert is given an individual reward of 0.001 for each frame he’s alive (0.6 total in a room lasting 10s), and Kai -0.001, to encourage Kai to try to tag Albert as quickly as possible. When we introduce the grabbable cubes we also give Albert an individual reward of +1 the first time he picks up the cube to make sure Albert actually starts using the cube (since without this, the rewards were too infrequent for Albert to learn to use it effectively).
BRAIN:
Albert and Kai’s brains are neural networks with 4 layers each (one input layer, 2 hidden layers and one output layer).
The agents collect information about the scene through direct values and raycasts. Every 5 frames they’re fed data about their position in the room, the opponent’s position, velocity, direction etc., and they also collect information through raycasts (a simplified version of eyes). The agent's eyes (raycasts) can differentiate between walls, ground, moveableObjects and Kai/Albert.
The agents' brains (neural networks) are given the data the agents collect from direct values and raycasts and use them to predict 4 numbers for the respective agent which control how that agent moves. An example of an output of one of the neural networks is: [1, 2, 0, 1], this would be interpreted as [1=move forward, 2=turn right, 0=don’t jump, 1=try to grab], so the agent being controlled by this neural network would try to move forward while turning right and grabbing.
The fact that we have two agents training simultaneously complicates things a bit, normally we’re able just update the agents brains every x steps, but if we did that for both brains at the same time then they would struggle developing multiple strategies, since reinforcement learning tends to be best at finding a single solution, that would lead to the winner dominating and the loser stuck doing the same strategy over and over. The way we tackle this issue is by using something called self-play. Since we use self-play, we technically only train one agent at a time, and swap which is being trained every 100k steps. When we’re training Albert, we use a recent model of Kai’s brain as his opponent, and to avoid there only being one strategy, we store 10 recent brains to use as opponents, swapping them out every couple thousand steps so that Albert learns to beat all of them and not just one. This results in a much more general AI that’s hard to exploit.
UNEXPECTED BEHAVIORS:
In room 1 Albert manages to break out of the room by exploiting a small hole in the hitbox near the top of the room, which was there because I didn’t make the hitboxes on the walls tall enough. Though Albert used it to escape, I’m not convinced he actually would learn to do it consistently. The challenge with this video is that it can be difficult to interpret the agent’s behaviors; Albert could be making certain unexpected moves as a way to exploit Kai’s poorly trained brain to get him to make bad moves, or Albert could just be making these unexpected moves because he hasn't trained enough. Albert was able to find the hole a few times, however he wasn’t able to do it consistently, this could be from either him not training long enough, his observations not making it easy to detect when he can jump out, or Kai quickly learning to counter him getting to the display in time.
In room 2 Albert also manages to glitch out of the room, and he was able to do this consistently. We made sure the cube grabbing functionality was coded as rigorously as possible, even with it automatically detaching the grab if the force exerted is too high, I couldn’t find a single way of exploiting it in testing, but Albert certainly didn’t have issues finding it.
Albert also had a couple moments of throwing the cubes at Kai and spinning with the cube to throw Kai out of the room, we didn’t even consider this being a possibility before training, AI’s able to come up with some really clever solutions to problems.
OTHER
Thank you so much to our amazing team that helped make this video! Jonas helped with setting up the character controls, Tyler helped create the clean grabbing functionality, Catt helped edit and Andrew and Steve helped solve any issues we ran into while making the video. If you want to meet our team and talk to all of us, join our discord server!:) discord.gg/qDRtuFe5gp
YOUR BACK!
I like you ;)
i love you vids
I ain’t reading all that!
first ig?
Albert did not merely "learn to play tag," he unlocked Ultra Instinct.
fr his dodges were crazy
DODDDGE!!!
what is tag ?
@@KarimY-119bruh
@@ClownEmojiii ?
"Albert, you can't escape"
Albert: "Okay, I'll force Kai to escape."
In a game where the most aggressive thing you can do is a light prod or moving a foam cube, Albert clobbering Kai into a different frame of existence is pretty Gamer of him.
@@NoxedwinAs opposed to Kai who subjects you to fucking Malevolent Shrine the attosecond he touches you
When does this happen
8:40@@forabba5776
@@forabba5776~8:39
Kai occasionally obliterating Albert's dead body shows that AI is capable of learning
*gamer rage*
4:32 He's literally teabagging Albert.
"It's Kai, the Blue Cube! He's loveable but he has an attitude on account of those frowny eyebrows! We hope he'll be a welcome addition to the game crew."
(200 sim-hours later:)
"We regret to inform you that the Blue Cube is racist now."
AI learns BM
@@rogerhepton1785 8:31 Albert got revenge
@@rogerhepton1785 bro learnt the backshot technique
what i learned:
evil is learned at a young age
what albert learned:
blue cubes are evil
someone ate the replies
Quran 21:33
َAnd He is the One Who created the night and the day, and the sun and the moon each one
floating (and moving) in an orbit
youtube mary and jesus in the quran and mohmmad in the bible and the Torah and the scientific
miracles of the quran and mohmmad in hindu scripture
…
according the bible that you have
(Matthew 4:1) Jesus was tempted
(James 1:13) God doesn't get tempted
(John 1:29) Jesus was seen
(1 John 4:12) No man has ever seen God
(Acts 2:22) Jesus was and is a man, sent by God
(Numbers 23:19, Hosea11:9) God is not a man
(Hebrews 5:8-9) Jesus had to grow and learn
(Isaiah 40:28) God doesn't ever need to learn
(1 Corinthians 15:3-4) Jesus dies
(1 Timothy 1:17) God doesn't die
(Hebrews 5:7) Jesus needed salvation
(Luke 1:37) God doesn't need salvation
(John 4:6) Jesus grew weary
(Isaiah 40:28) God Doesn't grow weary
(Mark 4:38) Jesus slept
(Psalm 121:2-4) God doesn't sleep
(John 5:19) Jesus isn't all powerful
(Isaiah 45:5-7) God is all powerful
(Mark 13:32) Jesus isn't all knowing
(Isaiah 46:9) God is all knowing
...................
.............
"Kai, that was aggresive"
Albert like 2 mins later: *throws Kai out of the map*
He mastered the legendary technology, *The cube*
Revenge
He became one with *THE CUBE*
Karma
Disgraceful QWERTY fail
Albert: "while you struggled on foolish pursuits, i studied the cube"
Had to be the 69th like for ya
The tungsten cube is the way.
@@darkwelder9736the density
@@malthe236 its so beautiful
@@frankaoooooooooooooooooooooooo open the curtains lights on
The 1v5 went crazy you can’t even lie
They say there's strength in numbers, but the winner proved that to be incorrect
So long as one survives, they haven’t lost. This is what people mean when they say that
Boy got launched almost out of the map again, BOUNCES OFF A WALL and proceeds to bamboozle the taggers so much they get mentally crippled
"If the Kais went at me together, I'd definitely have trouble."
"But would you lose?"
"Nah. I'd win."
Albert even learned to *_WALL-JUMP_* to escape the team of 5 Kai’s!
10:17 bro clutched the 5v1
Hey, I was gonna say that
10:15 I absolutely love that four of them just instantly died cause they could not comprehend what was happening fast enough, and one just instantly kicked into life or death mode and started doing insane strategies on the fly to avoid the army of death following him
he gained the strength of his fallen comrades
То просто был настоящий Альберт, который был с самого начала, а вот эти 4, были новечками
he seemed to have gotten in contact with a Kai less than a second before they all confettied, but he looked death in the face and waltzed out of the way
Best part: Albert learned fairly early on that the best escape strategy for avoiding mortality is ascension to a higher realm.
Very accurate observation! It appears to be the only way to survive in real life as well.
The science version of this answer is that the heat death of the universe, and death of our home star, is only avoidable with some kind of way to either reverse entropy (very difficult) or to escape this universe and go to a new one (also difficult). Scientists state that they are not sure if either are possible, but that does not stop them from trying to work on the problem.
The metaphysics and philosophic answer to mortality and the end of the universe is to ascend to a higher world, hence the purpose of this life is to prepare or to bring experiences and mature before we go to the next. This might actually not be completely incorrect if we look at near death experiences and events where people knew and saw things that should not have been possible.
The economic answer to the tendency for profit to decrease (economies gradually slow down and asset markets become saturated) is to escape to a new market, a new frontier, or develop new technologies.
Either of the above we see creatures of high intelligence searching for a way to escape mortality by ascending to a higher realm. Even the cute little boxes with eyes come to the same conclusion in their simulated world.
@@user-nu8in3ey8cnah
@@user-nu8in3ey8cYou used ChatGPT. The "Very Accurate Observation" said it all. I've used ChatGPT enough to know how it words stuff.
@@user-nu8in3ey8c
"If break, fix.
If fix cost same as replace, replace.
If replace scary, gtfo of here."
Sun Tzu said that, and so did George Washington when he tamed the first t rex.
good
albert perfectly understood that "to confuse your opponent you must first confuse yourself"
😆
Chat is the the super bone player
Lol
Can I quote this
@@yellowbacon69It is already a quote. Forgot by who though.
10:10
Albert winning the 1v5 was crazy bro in the next short he boutta start a family
Finna ask him to send THAT tape if ykyk 😏
i like how Kai kept emoting on Albert whenever he tagged him, very human
and the other way around, when Albert threw a cube at Kai.
This design is very human.
ai learned how to tbag
@@Blueshark8O9Easy to use
#JUSTICEFORALBERT
I love how Albert’s biggest breakthrough was just escaping the tag arena altogether
The only winning move is not to play
@@edgarallenjoe6494 you’ve.. Been..
@@trollguy2616 hit by
@@trollguy2616 TROLLED! You've been trolled, yes you've probably been trolled
literally breakthrough
6:25 Albert makes a wall, Kai breaks it, and Albert proceeds to send a block back at mach 10 speeds
i mean albert does know how to fling a block to make him escape the room
DODGEBALL!!! ⚾🥎🏀⚽🧶🏀🥎⚾⚽🧶🏐🏉🏈🏀⚽🥎6:25 999M/SEC
Bro they really do get angry I swear
Bro hollow purpled him
What was once a game of tag, now became a murder attempt from Albert sending a cube at light speed
1:10 Albert learnt to break Kai’s ankles
WOW
Soon he'll learn to be the epic ankle slayer
@@sapongjasmine09 Haha! Yes!
But Kai doesn’t have ankles
Thanks for 60 likes everyone!
Albert constantly throwing himself outside has to be the most hysterical strategy of all.
I mean. It works! Who can argue with the results?
This is actually a fairly common thing for learning algorithms to do. There was one I remember reading about which was tasked with finding landing approaches with minimal damage to the plane it was flying. Eventually it started flinging itself at the ground fast enough to overflow the damage calculator, resulting in a massive negative damage number.
@@stargate525That's actually hilarious!
@@stargate525Imagine giving it control of a real plane. The "safest" landing method would be a nosedive
@@deltap6967 News: "123432 deaths around the world due to Japan's planes nosediving into the ground at mach 19.23!"
I love how after the final battle ends, Albert goes to the timer and tries to use it to escape once again
When in doubt rely on instinct. The old ways of doing things exist for a reason.
7:06 "Now Kai's frustrated"
**explodes in frustration**
Gamer rage? More like AI rage
AI RAGEE
Actually relatable
😂
rAIge
10:00 did he just WALL JUMP?! I don’t think you noticed how cool that way
Kai wall jumped too
6:31 i love how Albert tries to get out of the map right there, it feels like an actual person trying a glitch after its been patched
XD
Oh I just love the fun little dynamics you can see here, like Kai exploding from frustration in a corner while Albert hangs out on the ledge, Albert being an absolute MENACE to level design, Kai stomping on Albert's remains after his victory, and Albert in turn throwing cubes at him aggressively 😂 I've wondered of statistical unfairness of a game of tag in a plain environment and environment with obstacles present, there's clearly a strong connection as seen in the first two levels. But soon enough these two brought so much chaos to the scene I forgot to be analysing and just enjoyed the show. We missed you, Albert and friends!
They're so funny
“‘Albert and friends’ THE SERIES”
@@VENTlLATION can't wait!
Lol
I love how you basically reimplemented the hide and seek experiment from OpenAI and ran into the exact same problems as them with the agents abusing the simulator physics
E
To be fair..... People would abuse stuff like that too
@@siliciaveerah9327exept most of these glitches are probably difficult to reproduce in terms of exact input, but thats not a problem for the ai😂
@@lazydk2654 oh ye of little faith
@@siliciaveerah9327 Lol I loved discovering stuff like this back when I played Roblox. Prop flinging never gets old though, it doesn't matter what game.
yknow it wouldve been a really good social experiment to see who emotionally supported which AI during this. Personally, I was rooting for Albert
ok maybe its just because of the annoyed eyebrows. I think if it wasnt for the annoyed eyebrows a lot of people wouldve rooted for Kai, probably me included
Me too. I felt bad for Albert in the beginning
I think it's pretty normal for humans to empathize with what we perceive as a victim of aggression.
@antonliakhovitch8306 yea
Same
Albert casually doing a 1v5 at the end, true gamer
Albert #3 coming in clutch.
average snd match in cod be like
@@Noxedwin he showed them the power of being the third strongest
He even pulled off a walljump
Albert casually doing clutch and exploit the game
Albert: I'm not locked in here with you, you're locked in here with me.
"Im not locked in here with you, I'll yeet either one of us out get bent loser"
The main reason how there jumping so godamm high is they jump then they jump on the edge but they keep the momentum from the last jump
I'm not locked in here with you, I'm just going to throw myself out of the map.
Also Albert: Im not locked out youre locked out!
*1 vs 5
Albert: "I like those odds"
Albert is a complete gamer after all
they’re definitely not even after all
I was so sure that "Kai" would win there 😅 but "Albert" had something to say about thay 😂
now im free to use my full power
8:40 albert said “I BANISH THY DEMON!!” To kai lmao 😭
5:30 speedrunner discovers new gamebreaking glitch, learns how to perform it consistently, smashes competition to bits
And it's literally cube jumping, one of the most famous glitches in Portal that speedrunners use!
@@sheersternfeld1914You're right lol
"He was treated like a loser but then he discovered a cheat SSS rank skill and become a god!"
underated
And finds another glitch at 8:40
Oh hey new character, and Albert is back to a square, my favorite version of him
Mine too! He's a happy cube!
Go square Albert!
Nah, Kai first appeared on the boxing battle short.
Its always been square albert~ he was just piloting a mech ;)
not walking Albert sliding Albert
4:30 i love how Albert is just celebrating like he already won and then Kai just said “nope”
and then starts teabagging him
9:46 Four of them instantly died of not knowing what to do, but the last one went full sweat mode, and activated his *ULTRA INSTINCT.* He has avenged his falled comrades.
Albert constantly T-bagging Kai is wild
Kai doing the same to Albert aswell lol
They've learned the TF2 Humiliation lap.
dang
@@NoxedwinBAHAHAHSHGHGHXK
What
8:25 Albert lures Kai to the edge, does a 360, proceeds to throw a cube at Kai at like mach 10 speeds, emotes, then spins on Kai.
*nice*
Albert: 360 noscope ez
Kai got reked
I love how even ai is capable of learning BM
he owned him fr
Albert learnt the rekt method
finally, the main villain was introduced
Those athletes from 100 meter dash are Albert's buddies, Kai is his enemy.
Everything makes sense now...
Uhm, well actually he was introduced in shorts about 2 months ago 🤓
Yes, but will he ever appear again?
I'm gonna draw them having s-
@@juanleon3875 Every hero needs a villain. He must be a reappearing character.
5:31 Albert learned to prop jump
Albert throwing the cube at Kai was funnier to me than it should have been.
Albert got his Limit Break. He was sick of always being on the defensive.
"Me? Run? Hell nah. Take this Kai!" *boink*
Imagine piloting a mech, but you dont know the controls, and your 'vision' is just 48 evenly spaced dots that change color based on what would be seen. You also get an electric zap if you do something wrong, but it would take a lot of trial and error to figure out what is 'wrong' and how to avoid it. Similar thing with rewards. Eventually you would figure out things like yhe time limit based on the shock and the dots resetting to the same spot each time.Thats what it's like to be Albert. Be nice to Albert
Light work, I'd win
You put me inside a mech and THEN try and tell me what to do? You fool.
*ROCKET PUNCH*
@@iforgotmyname1669zap.
Bro said Gundam 💀
isn't that just babies
Watching the AI cubes dance on each other's dead corpses is probably the funniest thing I've ever seen
Being toxic is a universal 𝒯𝓇𝓊𝓉𝒽
No matter the age, toxicity always hides underneath.
I just want to appreciate how you have framed the punishment and rewarding of a deep learning model in such a way that it’s very intuitive for a wide audience
8:40 Albert is savage. He woke up badass today.
Probably the funniest part of the video
Albert is god
*_iM a SaVoG yUh cLaSsiC gUcCi-_*
Bro really said “so long gay bowser”
@@themarkerchannel3170 FRRR
I love how there's the moment of similarity between this and the other AI hide and seek thing, where the AI do things not intended by the developer
I've seen that one too. AI shutting down paths, glitching out of the stage, and finding all sorts of creative ways to abuse the map.
Whats this thing about another AI?
@@soumickdas9674 OpenAI's hide and seek experiment video
@@soumickdas9674 ua-cam.com/video/Lu56xVlZ40M/v-deo.htmlsi=7DP7xwuaA7cj7qxC
@@soumickdas9674there's another video where the AI learns to play hide and seek, the runner learns how to glitch out of the map to escape
3:12 nah bro albert did the juke of the year
10:00
This is actually a great example of how the rules to a competitive game will greatly influence how the competitors will play the game, even beyond what the rules intended. Since Albert gets rewarded for not being caught, but doesn’t get punished for leaving the arena, he‘ll just do that, even if it goes against the original spirit of the game. Or like how in many modern martial arts the point system introduced to establish a winner allows for effective strategies that work in the environment of the sport but would not have been feasible in the context of combat that the art was initially developed for.
Fencing martial arts : learn to parry, dodge, and lunge at the right time
Olympic fencing meta : forgo defense, lunge as fast as you can
My favorite genre of A.I.:
No art thievery.
No job thievery.
Just A.I. learning how to play tag.
Edit2: Obviously, the first edit didn't help, so I'm just gonna delete that. Sorry y'all. 😓
This one was pretty messed up, bro forced them to fighttothe death
exactly
Ai doesn't steal anything, who said drawing is made for humans
@@scoreandspore.5606it does actually bc to make AI art the AI has to take art that already exists and smash it all together to make a new piece, and it’s been proven time and time again that the creators of these art engines LOVE taking art without consent for their database. Without human art, AI would never be able to make art, and as soon as AI starts pulling art from other AIs it’ll just poison itself.
@@redbassett2462 So it has to see art much like those human artists, to learn how to do it itself?
"bro, revive me!" the situation I'm in: 9:51
lol
3:57 NAH THE BACKSHOTS ARE CRAZY 💀💀💀💀💀
Albert juking kai out was hilarious
Albert’s versatility in the last round was CRAZY.
I love how human you can make AI feel/seem even with such simple mechanics and graphics. You made them especially more human with the addition of Kai with playing Tag... the subtitle text you add also helps make them feel human, like you're a human being the game announcer for these AI, narrating what they're doing to make them seem human.
Also, still love the theme of having the AI names just have some way of including "AI" in normal names: "AI"bert, K"ai"
thats an L
Artificial lintelligence
this has to be an AI comment
I love watching Albert just absolutely send it. Idk what it is but seeing him fly straight into space in half a second is hilarious you blink and miss him
Albert clutching at the end was ludicrous, had to show the youth how the oldheads used to play
4:32 Wow, Kai already learned how to teabag Albert. Truly the best timeline.
AI is capable of gamer rage
I mean, Albert teabagged Kai at 8:32 just after he threw a cube at him
rel
I love how when one wins the other jumps on their pieces
Teabag
5:20 Kai got a little angy 💀
8:30 even without human intervention, THEY INVENTED TBAGGING LOLLL
You can see the kai go through the actions at 4:32 too 😭
@@flosamuu nah he was cleaning up Albert's dead body (it was messy)
8:35 That wasn't very sportsmanly, Albert. I love it.
And here I thought cubes couldn't uppercut people in a game of tag
YEEEEEEET
The fact I am so attached to this little orange cube just shows how humans will pack bond with anything…
You hear stories of someone accidentally stubbing their toe on their Roomba, and having to coddle and apologise to it.
I think humans just have an affinity for Funny Little Guys.
Yeah. Anything that might to appear to be "alive" even though its completely inanimate or doesn't really have a mind of its own, we still feel the want or need to bond/apologize to these things xD probably the same way you imagined your little plushie to be sorta real
8:58 ALRIGHT I GET IT
That Albert 1v5 clutch at 10:13 is insane, Albert is a pro gamer
ONG
Fr
4:22
Albert jumping up and down after getting the cube stuck is actually so cute😭
Dude I was just wondering this morning how Albert the AI robot has been and you drop this only hours later, what a legend
Albert: has just a lil bit of an advantage
Also Albert: clutches a 5v1
These are fantastic. Inventive tests, great visuals, brilliant captioning/storytelling. Always a joy when a new one pops up in my subscription feed!
thank you so much!!:D
Why no pin?
8:30 they played enough time to become toxic teabaggers
He's teebagin
7:22 they disapproved the ad read
8:31 Albert my guy straight teabagged Kai ☠☠☠
This is a type of channel who post video every 4 months but you know that the video that will come out will be a banger
And this channel is the perfect example 🗿
The fact that Kai taunts Albert when he wins by doing a shuffle is so funny
7:36 bro the jukes are smooth, and the way he can glitch the cube every time goes to show how AI can calculate what to do, to do it perfectly
3:54 is this even AI moves💀
He was slowing down
theres no way kai learned the back forward toxic move 😭
@@jennynavel5222☠️☠️☠️☠️☠️
damn kai grew up being a toxic cod kid
Kai: I run around strong to catch Albert
Albert: I CONSISTENTLY GLITCH THE MATRIX
"I WIIIINNNNN" Albert screamed, falling forevermore in to the endless white abyss
4:14 Albert started emoting💀
nahh even the ai is foul
i love how kai gives backshots to alberts death
Final test, albert did alot of impressive things that most missed.
He used the boxes as a barrier and threw the boxes when a Kai is on it.
Double jumps.
Hides his back to a wall to no Kai can exploit his lack of back vision. Then jumping when a Kai is landing, and staying on the ground when a kai in jumping to exploit their vision, they can't see up or down, only front
6:11 I love how happy Albert looks here! He loves all the cubes!
jolly fellow! !
Making it so that we can't skip the sponsor without missing a chunk of the video. You clever bastard.
I'm just ignoring it anyway
that app is great tho
I prefer it
Great vid showcasing the AI learning a skill, I've always enjoyed watching these. However I am more impressed with how well the sponsor ad was implemented in such a way that it felt tied into the actual content, and engaging with content-relevant examples. Keep up the great work! I'd love to learn how to program AI that learns by itself.
00:47 kai also learned to teabag when he wins
"Well done, Kai!" 💀
Kai is Alberts number one opp the lore is expanding
Fun fact: depending on what font you use, Albert and Kai both have what appears to be the letters for AI in their names! Really cool easter egg
I think it's not really an easter egg, a coincidence at best
My co-worker showd me this a few years back.
They were working with about the same learning, a tagger and an avoider.
After some time they did things which he had not expect or considered at all.
It was rather interesting.
YOOO THE 1V5 CLUTCH AT THE END WAS INSANE THOUGH
Albert loves throwing himself out of the maps, he really knows how to think outside the box
Think outside the box using the box
@@JaymcJefty think outside the box using the box to get out of the box
@LouX453 while being a box
Think outside the box using the box to get out of the box while being a box and avoiding another box
@@kuutti256 exactly
Albert in the 1v5 literally says: Nah id' win
@2:15 This is called 'skywalking' - it's not necessarily a hack, but those who find the holes in the world can either fall great distances or walk on the sky itself. Well done, Albert and Kai. Final battle was like watching a Ms Pac Man expert. Excellent video.
Albert abusing the physics engine reminds me of a hide and seek ai video i watched a few years back
I believe I know exactly the video you’re talking about, I thought about it too!
It reminds me of the Henry stickmin collection!
@@MatthewMorris6148 Please do tell
@@RealCCre oh yeah the Toppat 4 Life ending
Yeah the OpenAi video
5:47 the way albert just ascended
5:15 5:20 7:03 8:08 8:24 can an ai like this grow to hate the other?
4:25 Albert really thought he won because of previous attempts interesting
Only if they have emotions then yes.
Probably,
> If you touch me I will be punished
> If I stop you from touching me I will be rewarded
> Why do you want to make me get punished
>Fuck you
Are we not gonna talk about how Albert threw the cube at kai and it landed ALMOST PERFECTLY in the corner?
On my rewatch they throw cubes at each other to escape or Kai throws it at a wall when he can’t get Albert and when either wins they bathe in each other’s blood or completely scatter the others remains with a cube and it just seems personal when stuff like that happens in these simulations and i know they can’t feel emotions but they really seem to hate each other.
2:12 NOO ALBERT WRONG WAYYY😭😭😭
The final 1V5 was crazy
Fr, Albert is such a clever lil cube for pulling that off! 👏
Fr 🗣️🗣️🙏🗣️🔥🗣️🔥🔥
Albert learning to leave the boundaries of his world (and launch his enemy out of it) was not the plot twist I was expecting, but a fun one nonetheless!
next he'll escape the simulation
8:35 Albert when he had enough:
Imaginary technique: Stay on the cube.
@@lucasdossantosrossi9834 bro went into an unlimited void 💀
finally we found who’s expanding the ai
I like it when AI/Neural Networks are used to do funny wacky stuff like this. Awesome stuff! :]
Ur everywhere lol
5:16 the cube flung out of the world😂😂😂
Cube fell out of the world
Nice castle profile
Watching Albert consistently break and exploit the game will definitely not have any real-world implications with AI alignment :D
We release AI's into the world, and a few centuries later they will all have ascended to a higher dimension by exploiting a glitch
5:54 bro escape the matrix