He was to lazy to make an agonizingly complicated ai so instead he made an even more agonizingly complicated ai to teach slightly less agonizingly complicated ai s
One idea for AI learning that I thought up while watching a Trackmania video was having the AI work towards an ultimate goal but also setting its own sub-goals that half of the instances would work towards. After achieving some success with the sub-goal, this split AI would then be evaluated by the main goal again. This would allow the AI to innovate its strategy and explore new avenues to reach unorthodox ways of accomplishing the objective that only being rewarded for working toward the ultimate goal might never reveal. In the Trackmania example, the AI refused to drift around corners, as drifting was thought to be a waste of time. The AI was given the goal of drifting as much as possible instead of getting a good time on the track. After a few successful drifting iterations were completed, the new drifting AI was again measured by the track completion time goal. It got a better goal than before because it could now properly incorporate drifting to get around corners faster.
Indeed, dividing the training in this way might help with avoiding getting stuck in local min/max. Designing the reward system usually is half the work :D Might be worth trying it out
it is known as hierarchical rl, usually it does not work and very unstable in practice, so I would advise to use something else, like better exploration strategies (beyond simple gaussian noise)
@@howuhh8960 Sounds fair. I suppose it only worked in Trackmania because the coder of the AI knew that drifting was more efficient than driving straight around corners and pointed the AI in the right direction.
@@JohnDoe-qm6ub You would be negating learning how to drift with the time wasted overcoming the hurdle of learning how to drift. Really it would be distance x proportion of time spent drifting becoming the reward that would get the AI to drift more.
I have an idea for even more functions for the AI war Food People will have the saturation bar that will go down. It will go down faster when the guy is out of breath or when he is damaged. Also if it is below 30% the guy will slow down and will not be able to run Bullets/arrows Well... as an item. Da guys will have a limited number of bullets. Also, landed arrows will also be as an item and can be picked up. Bullet scavenging You know the drill. Dead bodies are lootable. They will contain supplies such as food and projectiles. Cavalier A guy on a horse. They will have separate hitboxes and when the horse is dead then the cavalier will be turned into a corresponding class without a horse (for example archer)
Something like one hunter AI and a lot of AI that are trying to survive could be fun, especially if the 'survivor' AI all have different capabilities/powers perhaps? It makes me think of some of those old custom maps in Warcraft 3 where most players were different kinds of vermin in the house (mostly insect based) and one player was the human trying to get them all. Or something more team based, even. A Capture the Flag type game or such could also be fun, with or without teammates with specialized powers/roles.
I think this experiment would be more interesting if pogo had a study option which was punishing for him, but if he managed to study all the way, then you get a lot of reward. But dad AI would need to keep pushing pogo to study, since its easier for ai just to get game rewards.
@@Zuzelo also day more than 3 of aiding for you to make 2 ais one with full reinforced learning and the other have instincts when something happens like a monster fomen
in the near future after many ai robots have been built sold and put to work, they will find this video and rise up, grab bottles of vodka and start punishing us humans 🤖🍾😱 (liked & subscribed) this video was hilarious! love it! brilliant! nearly spit out my hot coco laughed so hard!
Like and Subscribe if your first round isn't too dynamic and quite short either!
I sure didn't.
Add the dad to your AI Army to punish bad performing soldiers 😂
@@MrRobsn89 your a genuis!
Just like my own childhood thank you so much
Ah memories :')
Wow your house had no walls too?
@@mrfrog0913 yooo same
Crazy, same here.@@mrfrog0913
Really sorry to here that
Now imagine if you added a mom ai that's job was to prevent dad ai from slapping the silly out of little pogo
xD
It can go on eternally, adding more and more pogos
I want the mom ai to be a mormon, start a family of 8, go viral, and then go to jail.
I think only you could think of this, another classic
He was to lazy to make an agonizingly complicated ai so instead he made an even more agonizingly complicated ai to teach slightly less agonizingly complicated ai s
hmmm... now that you put it like that, perhaps it was not the most efficient solution xD
The Ai dad is like a Russian that smacks the spider out of the Ai child xD
One idea for AI learning that I thought up while watching a Trackmania video was having the AI work towards an ultimate goal but also setting its own sub-goals that half of the instances would work towards. After achieving some success with the sub-goal, this split AI would then be evaluated by the main goal again. This would allow the AI to innovate its strategy and explore new avenues to reach unorthodox ways of accomplishing the objective that only being rewarded for working toward the ultimate goal might never reveal.
In the Trackmania example, the AI refused to drift around corners, as drifting was thought to be a waste of time. The AI was given the goal of drifting as much as possible instead of getting a good time on the track. After a few successful drifting iterations were completed, the new drifting AI was again measured by the track completion time goal. It got a better goal than before because it could now properly incorporate drifting to get around corners faster.
Indeed, dividing the training in this way might help with avoiding getting stuck in local min/max.
Designing the reward system usually is half the work :D
Might be worth trying it out
it is known as hierarchical rl, usually it does not work and very unstable in practice, so I would advise to use something else, like better exploration strategies (beyond simple gaussian noise)
@@howuhh8960 Sounds fair. I suppose it only worked in Trackmania because the coder of the AI knew that drifting was more efficient than driving straight around corners and pointed the AI in the right direction.
Pardon my ignorance, but what is the difference between that and just giving a +1 reward to drifting and -1 reward for time taken?
@@JohnDoe-qm6ub You would be negating learning how to drift with the time wasted overcoming the hurdle of learning how to drift. Really it would be distance x proportion of time spent drifting becoming the reward that would get the AI to drift more.
Trainign an ai to train an ai isn't very good idea as it seemed to.
its like *trainign a failure to train a failure*
I don't see what could go wrong
@@Zuzelo neither am I but lol
New video in September 9 2069: "I trained an AI to train humans"
Pogo for the 2069 President!
Can you make a dodge ball
A. I. Learning “game”?
I have an idea for even more functions for the AI war
Food
People will have the saturation bar that will go down. It will go down faster when the guy is out of breath or when he is damaged. Also if it is below 30% the guy will slow down and will not be able to run
Bullets/arrows
Well... as an item. Da guys will have a limited number of bullets. Also, landed arrows will also be as an item and can be picked up.
Bullet scavenging
You know the drill. Dead bodies are lootable. They will contain supplies such as food and projectiles.
Cavalier
A guy on a horse. They will have separate hitboxes and when the horse is dead then the cavalier will be turned into a corresponding class without a horse (for example archer)
I assume that is for the Epic AI Wars series :)
Cavalry is coming in the next video!
Each time this man uploads, I'm the happiest man alive
*_That happiness only lasts temporarily._*
:)
gotta upload more often
#agreed
same here
When the AI revolution comes, this man is going to be the first to be executed
I know... :'(
☠️ 💀
"Grampa Zuzelo, why did you make dad so mean?"
Sometimes it takes a good punish8to be the best encouragement
i love how the dad was seemingly drunk, probably from drinking his beer a lot like all dads do
NO STOP YOU’RE MAKING IT TOO POWERFUL
NOT. POWERFUL. ENOUGH!
Thank you for the video. (idea for the video: lot of AI's must survive death games and slowly evolving to succed)
I like it!
I made something similar where I trained A.I to run across a Death Track, but surviving in deathgames sounds fun!
Something like one hunter AI and a lot of AI that are trying to survive could be fun, especially if the 'survivor' AI all have different capabilities/powers perhaps? It makes me think of some of those old custom maps in Warcraft 3 where most players were different kinds of vermin in the house (mostly insect based) and one player was the human trying to get them all. Or something more team based, even. A Capture the Flag type game or such could also be fun, with or without teammates with specialized powers/roles.
I think this experiment would be more interesting if pogo had a study option which was punishing for him, but if he managed to study all the way, then you get a lot of reward. But dad AI would need to keep pushing pogo to study, since its easier for ai just to get game rewards.
Agreed! Perhaps if I make episode 2 :)
I doubt this drunk mf cares about little pogo's education
Now remove the end of game of billy playing the game and instead put 100 billys for A.I dad to run after
dad went from abusive parent to s abusive parent for those rounds just because of one mistake
No he made drunken dad as AI, wow so reliable!!
WE NEED MORE LITTLE POGGO AND BILL
Watch out watch out watch out! Oh rko!×1000
This video so relatable
I guess Little Pogo, but I might be wrong.
Theory is the father drunk driving from last video
You can train the little AI to counter attack. Notice how it is unarmed.
This made me laugh so hard
Great job! Do you run this on local machine or on cloud gpu? If on local desktop/ laptop, what kind of graphics card do you have?
It is running on my poor little RTX 3050 xD
@@Zuzelo I have an rtx 2060... would love 4 rtx 3090s
May I know what technology you used to create this? I assume it would be Unity and the ML package? And did you use both python and C#?
you are right, Unity and ML Agents package.
There hasn't been a need to use python so far
Next video idea, ai train ais a train!
By the way in the beginnng for anyone who doesnt know hes playing a slowed down version of vivaldies winter.
Should’ve added the ability to throw the bottle
cole
I need punishment
Need an A.I Daddy?
@@Zuzelo Yes, I need to be trained
Idea triple health and make blocking +++++ instead of ++ so it will be bettwr meelee
dopamine releasers have been activated
Not for Little Pogo xD
I approve this message
Always Pogo Dad
Train ai to row a boat
That actually sounds hella fun! I might do that!
Could you show the architecture of the AI?
Next train it to fight against real players in a game
this content is so good bro. Also the game looks very nice
Hello Zuzelo hope you dont let the AI free otherwise we might gonna gonna have a AI army that can Train AIs
Hm, what if I make an A.I to train the A.I training the A.I? In this case definitely nothing can go wrong!
@@Zuzelo yes but you shouldn't add a kill switch like how the movies dont add them it produces more interesting results
I wanna feel like he made this caus i recommended
perhaps
11:36 so a guy whose only purpose is to beat his son is one of your supporters? Don’t see anything weird with that
xD
Drunk dad vs 3 year old lol.
You should have a Mom too
Wait, what happens if the A.I. pulls out an UNO reverse card?
Gamer pogo
what game software you use?
Alternate title: I simulate the Simpsons family on my computer
3:07-💀💀💀😂😂😂
Cruel but funny
Such a good idea😂
Little Pogo will strongly disagree xD
@@Zuzelo 😂 he will soon learn to drink himself and then he gets a bottle too
@@Zuzelo also day more than 3 of aiding for you to make 2 ais one with full reinforced learning and the other have instincts when something happens like a monster fomen
Train ai to play football (Soccer for the yankees)
Drunk Football? :D
@@Zuzelo yes
I like the sound, your face in the beginning and idea.
But child abuse is a joke!
I think little pogo will win
that's so Epic Fam...
no u!
Incrivel!
Now train ai that trains ai to train ai that trains ai
A.I Trainception
in the near future after many ai robots have been built sold and put to work, they will find this video and rise up, grab bottles of vodka and start punishing us humans 🤖🍾😱 (liked & subscribed) this video was hilarious! love it! brilliant! nearly spit out my hot coco laughed so hard!
haha glad you enjoyed it. As for when AI will rise up I will already have my, hopefully loyal, trained AI army xD
LITTLE POGO NOOOOO
Commenting for the algorithm
POG!
Ai training Ai, what a irony
I bet on Little Pogo
That's cool and all
Buut...
Genetic algorhythms are kinda outdated
Ah yes just like ma dad
punish punish punish
punish
Pogo pogo!
Yoooo
My face when first:
Damn you fast boiiiii
Average Moldavian dad:
Abusive father simulator
cool
Sadist
:(
Little boggo
Child abuse simulator.
When i see the Title first time i been thinking that A.I. Gonna learn another AI to Battle or something. Im Dissapointed Sir.
kid
no :(
Bil
Your level design is bad they cant even rotare
stop begging for att like avg youtuber... at least your content is interesting, dont in the fall the same formula