AI is fascinating because it's smart enough to pick up on things like RNG manipulation, but dumb enough to get lost in a straight hallway. Really makes you think about what it means to think.
@agushernandezquiroga9064Күн бұрын
I wonder what would happen if you were to add a "speed" multiplyier to the reward function, where the sooner the AI gets a reward, the more points it's worth. Would it learn to speedrun the game?
@user-bi5lq1dj8gКүн бұрын
Man, you are crazy! That's insane!
@GageDash2 күн бұрын
Man I really loved this.
@Aznav-la-Betrave3 күн бұрын
AAAAAAAAA
@ApathyBM3 күн бұрын
This is pretty much a journal of how most of us played the game as kids
@CornelisCees3 күн бұрын
Ai being traumatized by depositing a pokemon lol. I basically learned English by playing these games when I was 8. I was still learning so when the daycare people took away my pokemon I did not understand the concept and thought they stole it somehow, and you couldn't get it back right away. I hated those people and never visited them again until years later.
@Taphosthewarlock4 күн бұрын
Could do without the misplaced social commentary on what would otherwise be an interesting video.
@NeftisIsHere4 күн бұрын
cry about it
@Taphosthewarlock4 күн бұрын
@@NeftisIsHere lol
@liperagegamer46825 күн бұрын
So, what is this AI? I mean, it's a site, an app? Something physical? Sorry if i look dumb, it's because i am dumb.
@asimnabil75655 күн бұрын
please make the ai finish the game. Mt moon should not be the end 😢
@TheBros2theend6 күн бұрын
Jesus loves you
@danielbociarski66336 күн бұрын
Surely you play up to the Elite Four and let it go free after that.
@zafron7776 күн бұрын
I think the reason AI develops a pattern walking around the corners is because you gave the incentives to explore, giving the AI incentives to explore for more different pixels, which can be found in the edges of the map.
@michaelkjellander93706 күн бұрын
It feels wrong to call it an artificial intelligence when it's so incredibly stupid and needs 5 years of pressing random buttons to get anywhere. Great video though.
@mygirldarby4 күн бұрын
It didn't take 5 Earth years.
@michaelkjellander93704 күн бұрын
@@mygirldarby 5 years of simulated game time, that's what he says in the beginning of the video. Try do imagine how good a human would be at the game after actively playing it for 45,000 hours.
@nuncamoods31157 күн бұрын
does that ai have capability to read and learn from the game text ? if not try that
@dickholemccumbershite84837 күн бұрын
I need to see this completed please I beg you
@MousechrisTFM8 күн бұрын
It stopped to look at the scenery, exactly like humans do It was petty and refused to press A for its defeat message simply just to not be told it lost It rage quitted avoiding brock because it lost too many times Your AI is just a literal human todler This AI is genuinely adorable
@Asidders8 күн бұрын
14:46 The music sounds so especially majestic here. What is it? Is it original from the game?
@iddqds8 күн бұрын
i hope they approved your master's degree dissertation
@VienerVater10 күн бұрын
"rather well-endowed server"
@froggeraj3311 күн бұрын
Any chance the ai will ever beat the game?
@alexhubbard763311 күн бұрын
This is how DJ Khaled would play Pokémon
@thenormalman203013 күн бұрын
omg so good
@I2ealTuber13 күн бұрын
This is amazing, cool experiment and very well made video!
@jasonbounds122215 күн бұрын
0:00 too many Ashes
@penintended921415 күн бұрын
Impressive!
@Happy_dog_grows16 күн бұрын
There are better ways to do this than Reinforcement learning. Ideally with a game as complex as pokemon, we would program the rule set into the model.
@gbsfranca12 күн бұрын
the entire point is for the AI to learn the ruleset by itself
@Gettoffmylawn2316 күн бұрын
I like how the towns look filled with ai, I like to think that all the AI are in the same world and the people are just freaking out as to why there are 1000 of the same kid walking into the walls of there house
@anonymousinternetuser751916 күн бұрын
I still come back to watch this every now and again dude. I love it so much.
@artisticcrossbreed17 күн бұрын
I'm absolutely dying for an update, I keep checking this channel every few months to see if there is another video
@nerdstemplar506317 күн бұрын
though ai looks like its doing what humans would do, it doesn't mean it's happening for the same reasons. AI writers should not cross over into philosophy without training, especially if you don't understand the difference between how you and your own program function.
@YodaWasSith18 күн бұрын
Man uploads one video
@doombergaming18818 күн бұрын
bow before roko's basilisk
@lukasruger604818 күн бұрын
This might be the most interesting, fascinating and satisfying video I've watched on KZfaq so far. Hats off, I'm looking forward to future videos!
@FingerinUrDaughter18 күн бұрын
"learning to play" and "learning a series of button combinations that will enable you to reach the end via throwing shit at a wall 10,000,000 times till you find which way to throw it and cover the entire wall", are not the same thing. this isnt AI, its brute force at the lowest shit tier level.
@Donorito16 күн бұрын
How do you think AI learns? Trial and error. Educate yourself before you make yourself look dumb lol
@poopsmithjones112 күн бұрын
this is like complaining about musicians trying a bunch of different notes and chords before deciding which fits best lol
@EyeOfCthulhu440020 күн бұрын
I really hope there was a universe where it did the mew glitch
@AlbertoNegri21 күн бұрын
wow amazing way of programming
@varglbargl21 күн бұрын
when you got to mt moon and gave up i looked at the video run-time, saw that it was only half way, and thought "oh okay so clearly he's gonna decide to do more at some point" and then no. you didn't. instead you did nothing. i was at 27 mins in when it hit me you were serious. like... if you had to guess, do you think maybe people clicked this video to see an ai play pokemon or to watch you give up and pivot to a tutorial on how you made the video. come the fuck on.
@Sol_Invictus77721 күн бұрын
Love the video, man! I can't wait to see what you do next!
@BosonCollider21 күн бұрын
You need to involve twitch in an active learning version of this
@davidschulz460721 күн бұрын
When comes next Video ?
@torfaro907521 күн бұрын
when i heard "reward" i thought of giving the computer a cookie when i did something right. like training a dog 😂
@computerzero772422 күн бұрын
How much can you tweak and micromanage the incentives before it's no longer "artificial"?
@Duesikazergaming22 күн бұрын
In future runs,make it so the Ai will have a fat reward for making a super effective move or boosting its Pokémon’s stats or lowering opponents stats
@lemmontree122 күн бұрын
Visualization and editing is top notch!
@AlponseE1ric23 күн бұрын
I come back to this video every month or so because of how well it is done, I would love to see more about this, even in other games like Gen 2 or 3! What differences would need to be made to make those work? Would any AI ever be able to find the Regis? How long would it take for them to get past the sudowoodo tree? I would love more of this, amazing work!!
@peterwhidden22 күн бұрын
hey! all good questions. folks have been working on some really neat stuff, on multiple gens! there will be more updates shared eventually :)
@autinjones719424 күн бұрын
it would have been hilarious if you used something from the red army choir for that opening gag. XD
@autinjones719424 күн бұрын
it would have been hilarious if you used something from the red army choir for that opening gag. XD
@joemurray24 күн бұрын
Was hoping it would beat elite four eventually - good video
@hherpdderp24 күн бұрын
It looks like rollecoaster tycoon when you open the park. Can you emulate the game boy connection to have the AIs battle themselves?