AI Learns to steal

Подписаться 24 тыс.

Просмотров 307 тыс.

50% 1

Based on a true story!
Key Hyperparameters for those interested:
type: PPO
Batch Size: 512
Buffer Size: 4096
Hidden Units: 512
Hidden Layers: 4 (yep, 4 actually got me the best learning at a decent rate, typically I'd try with 2 or three layers first)
total training time:
approx 8.4 hours
20,800,000 steps
music:
1 - 368 - Dyalla
2 - All I Am - Dyalla
3 - Beyond - Patrick Patrikios
4 - TORSION - Density & Time
5 - AETHER - Density & Time
6 - Organic Guitar House - Dyalla
textures from:
PBR Material Bundle Vol1 - Cole
100+ PBR Materials Pack - Integrity Software & Games
AllSky - 220+ Sky / Skybox Set - RPGWHITELOCK
and some bad ones from me!
models from:
Low Poly Ultimate Pack - POLYPERFECT
Low Poly Disco Bar Pack - GOLS Consulting

Наука

Опубликовано:

18 дек 2023

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 448

@Lozoot2 5 месяцев назад

Dingus is not a thief, he is a GREAT ASSET to the company

@kaderobertson2489 5 месяцев назад

Hopefully he doesn’t find any flower men.

@adora_was_taken 5 месяцев назад

weeeee looooove the company

@binjimonanimations 5 месяцев назад

Asset-Great great asset

@8stormy5 5 месяцев назад

great great asset great great asset

@turkeybywhatmeans 5 месяцев назад

@@adora_was_taken WEEEEEE LOOOOVE THE COMPANY

@kalandillon8320 5 месяцев назад

Imagine if a dude broke into your house, did sick flips for 3 minutes then left without saying a word.

@I_CANSPEAK_IN_CAPS 4 месяца назад

I can imagine that

@soup9242 4 месяца назад

I would respond by doing nothing.

@thatprotogen2456 3 месяца назад

@@soup9242 popcorn

@ZeSillyGuineaPigGUYFEVEJ-YUMBO Месяц назад

@@soup9242 I would respond by joining him because BINGUS those are sick flips

@JamesJamesW 5 месяцев назад

Sad to see Dingus fall on hard times.

@schneebeingme8758 5 месяцев назад

And on stairs

@SpammingY-pp2ru 5 месяцев назад

And off of the stai-- oh you got to it first

@epicman6827 5 месяцев назад

Floors*

@HatInInternet 5 месяцев назад

Seal :3

@bitblit 5 месяцев назад

I imagine Dingus was given no memory which explains why Dingus immediately moves on when objects fall out of view. With that in mind, going up the staircase and jumping off is actually a brilliant strategy because that path has more visual coverage than anywhere else in the room.

@cardboardking577 5 месяцев назад

Dingus hasn't developed object permeance

@Marscandy1 5 месяцев назад

⁠AI learns to get around short term memory loss

@Yesnaught 5 месяцев назад

I think it's more likely that he recognises moving valuables is rewarding, but does not realise he gets *more* for completing delivery.

@Bulldogg6404 5 месяцев назад

I am on board with this theory @bitblit, also in supposing that there's rewarding going on for exploration. It seems that Dingus does not know where all the valuable items are from the start and must first locate them, which would suggest that any maneuver which drastically gathers information about where the valuable items are (such as eliminating the most space without valuable items) is rewarding enough to do repeatedly.

@ToonedMinecraft 5 месяцев назад

I'd be interested in seeing Dingus try to rob from completely different buildings with this same training.

@Nevernamed 5 месяцев назад

I'd love to see him try and steal in even more environments, with uneven or unnatural terrain, or more hazards.

@melvinthemussel 5 месяцев назад

ye like guards

@GTD_GameTilDead 5 месяцев назад

bro wants to see the world crumble before his eyes 💀🗿

@elizathegamer413 5 месяцев назад

maybe fire exits

@user-ik6dg9uk3u 4 месяца назад

Lasers on the floor

@julianhernandez5732 4 месяца назад

@@elizathegamer413 a few thumpers for good measure

@morgan3392 5 месяцев назад

His addiction to boulder rolling has led Dingus to a life of crime.

@KeepPolandPolish 5 месяцев назад

Maybe him liking pearls at start is ptsd of some sort

@SkillfulLupus 5 месяцев назад

if i ever see 3 stairs i will now purposefully avoid the middle one at all times even if it's an easier path

@McTuber42 5 месяцев назад

I wonder if Dingus would be able to easily generalize to new maps, or if he's just learned how to beat these particular maps. Future video idea?

@Dingus_Labs 5 месяцев назад

It's a good question, I'm curious myself, my guess would be he'd likely need to learn a wider pool of maps if new ones were substantially different. But I have a trained model now so I can stick it into some new maps and see how it behaves

@justletmefailinpeace9099 5 месяцев назад

@@Dingus_Labs That might make a decent follow up video to this one. Just following the adventures of Dingus the Thief as he robs a liquor store of all its speakers.

@thinkublu 2 месяца назад

@@Dingus_Labsoh, that's something I'd be really interested in seeing

@Squarepy 2 месяца назад

@@Dingus_LabsI feel like you shouldve added a guard that also trained like dingus but catching dingus instead and the guard traine dsame rate as dingus and was named "Bingus"

@vrchhu4066 5 месяцев назад

I have a feeling the stairway loop has something to do with the reward system in some way. Maybe pushing down a valuable generates a high reward value as opposed to just nudging it like in the beginning, since it travels much closer to the car, thus leading Dingus to associate the stairway with that rewards spike.

@kolmo3182 5 месяцев назад

I think your right... Is the moving items closer to the door working right? It looked like he would get close enough to git the reward and then run off 😅

@Dingus_Labs 5 месяцев назад

could be right there, I tried to keep the "move the object towards the entrance" reward low so that it wouldn't overly impact later behaviours in training that got much higher rewards, but it may still have had a long term impact on his behaviours.

@kolmo3182 5 месяцев назад

@@Dingus_Labs sounds like it's going to be a reset, go back a save, or remove the reward and penalty for moving it until you can bend hem back some. but most of the time unless it's part of the mission to keep the IA's memories intact it well take 5 or 6 times longer to unlearn something then restart sadly

@vrchhu4066 3 месяца назад

@@Dingus_Labs maybe if you make the hitbox of the van for putting away the loot really tall and have dingus track the closest path that could solve it? Then the items descending due to gravity wouldn't generate as many points

@neoncreeper1287 5 месяцев назад

all future dinguses should be granted small rewards for doing sick flips from staircases because those really were some sick flips

@icebreaker690 5 месяцев назад

If he struggles with this imagine this with guards

@punishedkid 5 месяцев назад

9:13 Reminds me of video game speedrun brute forcers that find crazy tricks like this by testing every possible permutation of inputs. Very cool discovery.

@FeverBonus 5 месяцев назад

iirc, this also happened in the Open AI hide and seek demo. The seekers learned to abuse the physics engine to launch themselves over obstacles, even though they only had directional inputs to work with.

@Dingus_Labs 5 месяцев назад

I remember that vid, such a classic.

@r.henryjr.1533 5 месяцев назад

Sounds cool, what's the video?

@SusDoctor 5 месяцев назад

I love how dingus was literally just any player of a game goofy around at the start

@Fighting.Flower 2 месяца назад

I love the part where Dingus starts chugging wine and shoves the speaker as far as he can under the table. I can picture an actual incompetent thief getting wine drunk and violently proceed to force the electronics under furniture.

@zacharymacleod1146 5 месяцев назад

I want to see one with two competing AIs training concurrently, like a cop AI vs a robber AI

@thinkublu 2 месяца назад

I actually wonder how that'd go, huh Whether they are even capable of adapting to each other

@nathanreeder9716 5 месяцев назад

Honestly, I’m surprised it went so smoothly. My guess is that you left out a lot of the trial and error that I know goes into this-I’ve heard of people running simulations for literal days and coming out with an ai that was only slightly better than before.

@Dingus_Labs 5 месяцев назад

There were 67 prior runs performed before I had a model that was reliable enough I was happy to make a video with! I had to redesign reward functions and the actual gameplay a few times as part of that and tweak a lot of hyperparameters, I also for the first time needed to increase the number of hidden layers to 4 this time before I saw really good progress. A number of my earlier attempts did yield an AI that could solve all levels, but not reliably enough for my liking!

@bingusbongus9807 5 месяцев назад

seeing how high he got id love to see a video that rewards him for height but has no obvious ways to do it too see if he can wall run consistantly

@LemonPlayz101 5 месяцев назад

A good representation of how I learn how to play a new game. Go dingus...

@ethanwilde4716 5 месяцев назад

Dingus may be a idiot but he's our idiot. Never change dingus. Never change.

@Memer9456 2 месяца назад

hes struggling to resist the voices’ demands to climb up the stairs and flip off the balcony

@melody3741 5 месяцев назад

I thought you were gonna convince an ai to make the moral decision to steal

@nicolaszanon3337 5 месяцев назад

next episode, DINGUS LEARNS HOW TO ESCAPE THE POLICE

@SunshineBurrito 5 месяцев назад

So sad seeing dingus have to resort to this 😔

@thegenericnerd6832 5 месяцев назад

Would love to see how he preforms in a new map he never got to train in

@FurryNonsense 5 месяцев назад

5:50 That laugh kills me 😂

@KangaGamer 5 месяцев назад

Now AI are putting thieves out of work. A thought that simultaneously sounds great and scary.

@gungle2595 5 месяцев назад

you should do a video where dingus has anxiety and randomly gets negative values for absolutely no reason and see what happens

@stefanvasile199 5 месяцев назад

Ai becomes romanian

@itsmelaurin 5 месяцев назад

This is awesome! Didn't think the agent would learn this quickly. Also, thank you so much for including the mlagents hyperparameters in the description. Much appreciated 👌

@aberrantcurse8551 3 месяца назад

One could argue they're already very good at that

@ninjakiwigames5418 5 месяцев назад

So glad I watched your old videos before you removed them. You've improved a lot!

@Dingus_Labs 5 месяцев назад

thank you! The old vids are still available on a playlist for the channel, I just wanted some level of seperation because the new content is pretty different in format to the old content and felt them being intermingled could cause some confusion.

@bonkatomic 3 месяца назад

I think the reason he kept going down the stairs was because he got rewarded for going fast, and falling was the fastest way to move in his reality.

@griffongrondin904 5 месяцев назад

This is one of my favorite channels rn, im suprised its not larger, I love Dingus

@BobsiTutorial 5 месяцев назад

Great video as always. Would love to get something like this setup and play around with it in multiplayer. Could be interesting to see the AI having some basic understanding from the beginning, and then see how quickly it can learn. Like a tutorial or intro sequence for us mortalt. So for example a pre-recorded playthrough but with the AI still getting the rewards prior to the AI taking control, just so it got a "taste" of what works and what doesn't. A kickstart one might call it.

@wyvern2112 5 месяцев назад

it'd be interesting to see a dingus that combines all the previous ai's

@lilithcole 5 месяцев назад

DINGUS I NEEDED YOU IN THESE TRYING TIMES

@maplefoxxo 5 месяцев назад

Wow your acc is growing lol!! So excited to see another video

@Lucasthepookus 4 месяца назад

Thought this was dank pods at first. Love the video bro

@foolsgold_2558 5 месяцев назад

good to see Romania putting some effort to expand the limits of ai

@feralcatboy7628 5 месяцев назад

is this why dingus was sent to the underworld

@PotentSmokeKTv 5 месяцев назад

Dingus was just checking if there was fall damage. Smart guy

@liraz2298 3 месяца назад

AI is already really good at stealing

@end_slayer 3 месяца назад

10:40 Him talking to dingus feels like the narrator talking to Stanley.

@nocluebruh3792 4 месяца назад

sick flips, Dingus!🔥

@rowanstree8499 2 месяца назад

Thanks for the video! This data will be very useful for my new ai powered mech 😊

@WoolyCow 5 месяцев назад

but the real crime was dingus stealing our hearts...

@Vi4Valentin 5 месяцев назад

great watch, thank you for this video! I hope your sickness has completely left you

@peyton-rproductions380 5 месяцев назад

I love to see another installment in the dingus franchise!

@danzal13 5 месяцев назад

This is really underrated!!

@IcanReadCanYou 5 месяцев назад

This is the most fun AI video I've ever seen.

@emilygordbort7300 4 месяца назад

You should've told Dingus he was an artist, he would've figured out how to steal 50% faster

@theguywhoasked9046 3 месяца назад

this is like playing any games for first time

@izuwi1 4 месяца назад

Big fan of the videos, I think it’d be neat if you elaborated on how the ai works and/or the inputs dingus gets

@kevinleroy3155 4 месяца назад

This man IS boosted with the ytb algorith but this level of excellent content i love it

@KeozFPV 4 месяца назад

Did you maybe give it an award evertime it sees the object? That would ecplain the flips and circles.

@godwin972 Месяц назад

So, an AI image generator, basically? Thank you, thank you, I'll be here all week

@rubbersplat2846 5 месяцев назад

I give my life for glorious dingus nation

@alecpetsche1104 Месяц назад

I really like that he found a valuable item and was rewarded for, but coincidentally flipped off the second floor, and was forever convinced that flipping off the second floor was good, so he did it whenever he was lost

@townbug 5 месяцев назад

i love your channel.

@mikeemous1410 5 месяцев назад

This guy's RU-vid channel is gonna be the entirety of our universe's terminator lore

@dylanherrera5395 5 месяцев назад

This and epic ai wars are now my go to places for all things ai entertainment

@IsaacDaBoatSloth 2 месяца назад

i think he kept doing kick flips because he associated the reward not with the wine but instead with the drop off the stairs

@Bagelvr63292 3 месяца назад

Missed opportunity to combine the video where dingus avoids the enemy agents and this

@lamarepository248 5 месяцев назад

I’m so proud of your AI son.

@thevillager9370 5 месяцев назад

Sick flip, Dingus!

@JulianDaEpic0 5 месяцев назад

OMG HE'S BACK

@rex_ink 4 месяца назад

Dingus really said "W I N E... F L I P S..." Within the first 20 minutes of their life

@ARandomTrout356 4 дня назад

Imagine just being hired to just say "too dang slow Dingus!" every 200 seconds

@ninjojninjoj635 5 месяцев назад

I love your videos

@blo0t260 25 дней назад

This man just made a lethal company bot

@greatercanada3020 5 месяцев назад

The switching between the different Dinguses testing gives me major Aperture Science vibes

@Object_Reference 5 месяцев назад

Now he's so good with the basics would be amazing to see him take on bigger maps with security cameras/patrolling agents 😅

@oldbones7148 5 месяцев назад

Great experiment

@bennutt5050 5 месяцев назад

should give Dingus a friend

@gabrielv.4358 2 месяца назад

Great! Diserve more views.

@gwusbwth6230 5 месяцев назад

Would you be able to reuse the ai learning from another project to give Dingus a headstart on a challenge in the future? Like maybe the box pushing ai would have given Dingus a good idea of how to push the loot around his environment.

@Dingus_Labs 5 месяцев назад

You can definitely build on top of existing models (in multiple ways), the main difficulty is that in order to reuse a model it needs to have the exact same neural net properties and use the exact same inputs and outputs in order to be compatible with the new environment, often times a new environment may require changes to one of these 3 things in order to perform optimally which means starting from scratch.

@lordpie6759 5 месяцев назад

I would love to see guards added

@rslasher2270 5 месяцев назад

that ai is so quick it learns it absolutely no time. damn

@Jazkal-V420 5 месяцев назад

Hmmmmmmmmmm, he's new but he's got it.

@blacklight683 5 месяцев назад

1:28LIES! we need dingus guitar

@KirbosPlanet 4 месяца назад

AI learns to borrow things extremely unethically

@MurrayHouston-iv6fp Месяц назад

More powerful than the will to win is the courage to begin.

@Fred_the_1996 2 дня назад

Or the courage to be born black

@SucculentSpaz 2 месяца назад

I would pay good money to see this entire video remade with a real life actor, although I can't help but think this is just what an actual burgler is doing as they're looting.