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.
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.
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.
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
@@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.
@@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"
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.
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 😅
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.
@@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
@@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
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.
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.
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.
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!
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.
How would one get started training 3d models like this? To be clear, I have 3d skills in Blender, but besides that, I have literally zero clue how I would start. Any insight would be greatly appreciated!
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 👌
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.
I refuse to believe it's a coincidence that the ai is named dingus, the gum was james', and the video was followed by a short video of a pet doing silly things. Please be some sort of dankpods reference.
Oh my god I did not make the james connection until you mentioned it! I discovered dankpods this year after a few sad things happened and am hugely grateful that I did, Dingus already had his name by then, but I'm originally from South Australia as well so we share some of the same slang. The pet at the end is inspired by dankpods though, we got our puppy this year and I had too many videos of him being a complete goof to not add them!
@Dingus_Labs I love that at least one of the things I mentioned was actually inspired by dankpods. If you haven't already, definitely check out all his other channels. I'm sorry to hear about the tough times, but I'm glad you made it through and wish you nothing but the best.
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
I see that these balls keep rolling for a moment after being pushed (with a possibility of getting the off-screen score?). Maybe he pushed something and it went through the entrance (off-screen) while he was climbing the stairs, which created a big bias early on? 😀And made him stairs loving player😀
Crazy to see how dingus is initially trying random things, like going up the stairs, to try to get rewards - just like how if you put a human in a room with a bunch of stuff and told them to solve it, they would try random stuff. Even more crazy to see is that once dingus is successful, it still unnecessarily goes up the stairs before depositing each item, because when it first ever deposited an item it went up stairs beforehand. So dingus pretty much created a ritual, seeing the mission to be to go up stairs and then deposit, instead of just depositing. This might explain why humans created rituals for things that are out of our control (rain dances) or for things that have complicated patterns that are hard to see at first.
Imagine if a dude broke into your house, did sick flips for 3 minutes then left without saying a word.
I can imagine that
I would respond by doing nothing.
@@soup9242 popcorn
@@soup9242 I would respond by joining him because BINGUS those are sick flips
Sad to see Dingus fall on hard times.
And on stairs
And off of the stai-- oh you got to it first
Floors*
Seal :3
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.
Dingus hasn't developed object permeance
AI learns to get around short term memory loss
I think it's more likely that he recognises moving valuables is rewarding, but does not realise he gets *more* for completing delivery.
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.
I'd be interested in seeing Dingus try to rob from completely different buildings with this same training.
Dingus is not a thief, he is a GREAT ASSET to the company
Hopefully he doesn’t find any flower men.
weeeee looooove the company
Asset-Great great asset
great great asset great great asset
@@adora_was_taken WEEEEEE LOOOOVE THE COMPANY
His addiction to boulder rolling has led Dingus to a life of crime.
I'd love to see him try and steal in even more environments, with uneven or unnatural terrain, or more hazards.
ye like guards
bro wants to see the world crumble before his eyes 💀🗿
maybe fire exits
Lasers on the floor
@@elizathegamer413 a few thumpers for good measure
if i ever see 3 stairs i will now purposefully avoid the middle one at all times even if it's an easier path
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.
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.
Looking back at it now it looks like an addiction
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?
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
@@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.
@@Dingus_Labsoh, that's something I'd be really interested in seeing
@@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"
all future dinguses should be granted small rewards for doing sick flips from staircases because those really were some sick flips
If he struggles with this imagine this with guards
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.
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 😅
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.
@@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
@@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
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.
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.
I remember that vid, such a classic.
Sounds cool, what's the video?
I love how dingus was literally just any player of a game goofy around at the start
I want to see one with two competing AIs training concurrently, like a cop AI vs a robber AI
I actually wonder how that'd go, huh
Whether they are even capable of adapting to each other
hes struggling to resist the voices’ demands to climb up the stairs and flip off the balcony
5:10 this just makes me want to see “teaching an AI how to become an alcoholic”
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.
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!
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
You should've told Dingus he was an artist, he would've figured out how to steal 50% faster
Dingus may be a idiot but he's our idiot. Never change dingus. Never change.
A good representation of how I learn how to play a new game.
Go dingus...
Now AI are putting thieves out of work. A thought that simultaneously sounds great and scary.
I thought you were gonna convince an ai to make the moral decision to steal
So sad seeing dingus have to resort to this 😔
next episode, DINGUS LEARNS HOW TO ESCAPE THE POLICE
Would love to see how he preforms in a new map he never got to train in
So glad I watched your old videos before you removed them. You've improved a lot!
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.
Ai becomes romanian
you should do a video where dingus has anxiety and randomly gets negative values for absolutely no reason and see what happens
One could argue they're already very good at that
but the real crime was dingus stealing our hearts...
This is the only acceptable kind of AI learning, I would be ok if Dingus stole my job. He stole my heart already
This is one of my favorite channels rn, im suprised its not larger, I love Dingus
5:50
That laugh kills me 😂
Dingus drinks wine, get drunk, and pushes a speaker aimlessly into a table for no reason 5:09
5:15 dingus got drunk form the wine and forgot how to thief
Dingus really blew his own mind, got confused, and immediately went to try and jump off the tallest thing near him. Wow.
AI learns to borrow things extremely unethically
it'd be interesting to see a dingus that combines all the previous ai's
How would one get started training 3d models like this? To be clear, I have 3d skills in Blender, but besides that, I have literally zero clue how I would start. Any insight would be greatly appreciated!
Dingus was just checking if there was fall damage. Smart guy
is this why dingus was sent to the underworld
Missed opportunity to combine the video where dingus avoids the enemy agents and this
now train a cop to catch dingus
mother: you will get married and raise children!
the only children im gonna raise:
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 👌
good to see Romania putting some effort to expand the limits of ai
DINGUS I NEEDED YOU IN THESE TRYING TIMES
Thought this was dank pods at first. Love the video bro
They call me dingus
Dingus learns to gladiator fight
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.
Dingus really said "W I N E... F L I P S..." Within the first 20 minutes of their life
i think he kept doing kick flips because he associated the reward not with the wine but instead with the drop off the stairs
should give Dingus a friend
1:24 what if dingus learned to play guitar
10:40 Him talking to dingus feels like the narrator talking to Stanley.
AI Learns to do SICK FLIPS.
Childhood simulator with strict parents
I refuse to believe it's a coincidence that the ai is named dingus, the gum was james', and the video was followed by a short video of a pet doing silly things. Please be some sort of dankpods reference.
Oh my god I did not make the james connection until you mentioned it!
I discovered dankpods this year after a few sad things happened and am hugely grateful that I did, Dingus already had his name by then, but I'm originally from South Australia as well so we share some of the same slang.
The pet at the end is inspired by dankpods though, we got our puppy this year and I had too many videos of him being a complete goof to not add them!
@Dingus_Labs I love that at least one of the things I mentioned was actually inspired by dankpods. If you haven't already, definitely check out all his other channels. I'm sorry to hear about the tough times, but I'm glad you made it through and wish you nothing but the best.
Ai is really taking all our jobs
damn he really dingused at the end, really showed us that dingus mind set at work.
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
I give my life for glorious dingus nation
I see that these balls keep rolling for a moment after being pushed (with a possibility of getting the off-screen score?). Maybe he pushed something and it went through the entrance (off-screen) while he was climbing the stairs, which created a big bias early on? 😀And made him stairs loving player😀
I need dingus as a lethal company partner lol
i think Dingus confused the moving loot closer to the exit with doing sick flips so now he has found a new purpose in life.
Dingus:try not to do sick flips challenge (impossible)
Average Romanian Training Regimen
5:30 he probably thought that stair jump + item = reward lol. Ai is fascinsting
This guy's UA-cam channel is gonna be the entirety of our universe's terminator lore
It took him 10k seconds to do what a kid can do within 1m of playing
Truly kids are our future!
yes to child labo- i mean raising children for wor- i mean to be the future of wor- i mean humanity@@Dingus_Labs
Dingus learns to not fool around at work
ia learns how to comit planetary crimes
Train Dingus for war
AI if finally getting good
1:28LIES! we need dingus guitar
I love Dingus.
I think someone already taught AI to steal because it stole my art portfolio.
Crazy to see how dingus is initially trying random things, like going up the stairs, to try to get rewards - just like how if you put a human in a room with a bunch of stuff and told them to solve it, they would try random stuff.
Even more crazy to see is that once dingus is successful, it still unnecessarily goes up the stairs before depositing each item, because when it first ever deposited an item it went up stairs beforehand. So dingus pretty much created a ritual, seeing the mission to be to go up stairs and then deposit, instead of just depositing.
This might explain why humans created rituals for things that are out of our control (rain dances) or for things that have complicated patterns that are hard to see at first.
definitely love an AI that's honest about it stealing from people :)
I’m so proud of your AI son.
The switching between the different Dinguses testing gives me major Aperture Science vibes
it would be a cool idea to see something like this but with a security ai that is also learning how to keep the robber out
Welcome, dingus, to romania.
Did you maybe give it an award evertime it sees the object? That would ecplain the flips and circles.
It’s really amazing that he try to move two objects at the same time!!👍
it would be cool if you did more levels that had guards for him to sneak past
9:13 dingus the speedrunner
AI learns to be me
Yingus is here. Sisyphus didn’t teach him a lesson yet
This is the most fun AI video I've ever seen.
Imagine just being hired to just say "too dang slow Dingus!" every 200 seconds
More powerful than the will to win is the courage to begin.
Or the courage to be born black
this is like playing any games for first time
i feel the dingus lore growing
it's all fun and games until dingus tells you to bite his shiny metal ass
that ai is so quick it learns it absolutely no time. damn