AI learns to push boulders up insane hills

แชร์
ฝัง
  • เผยแพร่เมื่อ 25 ธ.ค. 2024

ความคิดเห็น • 1K

  • @revimfadli4666
    @revimfadli4666 ปีที่แล้ว +8322

    One must imagine Dingus happy

    • @Dingus_Labs
      @Dingus_Labs  ปีที่แล้ว +944

      Legends say he was happily pushing boulders even before he was put into this strange simulated environment.

    • @christianottley8542
      @christianottley8542 ปีที่แล้ว +253

      One must imagine dingus upside-down, its hilarious

    • @Scratchydoesmusic
      @Scratchydoesmusic ปีที่แล้ว +38

      ​@@Dingus_LabsHmmm...

    • @totrox2445
      @totrox2445 ปีที่แล้ว +65

      I knew this comment will be here as i saw the title of the video.

    • @The_Cheez
      @The_Cheez ปีที่แล้ว +6

      Dang it. He beat me to it

  • @zawarudo497
    @zawarudo497 ปีที่แล้ว +2707

    it acts so convincingly distraught whenever it loses the ball

    • @ShrimpFry_Cute
      @ShrimpFry_Cute ปีที่แล้ว +5

      He lost his ball. Why do you think he’s not distraught. I would freak out if I lost my ball too.

    • @frowner_and_co
      @frowner_and_co ปีที่แล้ว +169

      He so sad 😢

    • @nicolasn12
      @nicolasn12 ปีที่แล้ว +29

      boulder*

    • @alansmithee419
      @alansmithee419 ปีที่แล้ว +240

      It doesn't know what to do so it acts chaotically.
      Humans do the same. We just also get distressed because our brains recognise the problem.
      We don't act chaotically because we're distressed, it's just that acting chaotically and getting distressed often have a common cause - we don't know what to do.

    • @manboy4720
      @manboy4720 ปีที่แล้ว +80

      @@alansmithee419 so you're saying that dingus is the next stage in human evolution?

  • @KaufmoTheCIown
    @KaufmoTheCIown ปีที่แล้ว +3699

    Give Dingus a top hat that progressively gets taller every video.

    • @paper177
      @paper177 ปีที่แล้ว +89

      YES

    • @paper177
      @paper177 ปีที่แล้ว +178

      but wait nono one that gets taller everytime he gets a reward

    • @revimfadli4666
      @revimfadli4666 ปีที่แล้ว +174

      @@paper177 then one no longer needs to imagine Dingus happy, for he is actually happy

    • @paper177
      @paper177 ปีที่แล้ว +19

      free hat

    • @AnUnfortunatePotato
      @AnUnfortunatePotato ปีที่แล้ว +48

      @@paper177is that dimmagingus, owner of the dimmsdale dimmadingus?

  • @exLightningg
    @exLightningg ปีที่แล้ว +1160

    I always enjoy these machine learning videos but at the end I always wish they'd run the trained AI through all the levels/courses again.

    • @garchamayne4254
      @garchamayne4254 ปีที่แล้ว +121

      Definitely. Want to see the difference between the new and final ai

    • @mondongoloco7902
      @mondongoloco7902 ปีที่แล้ว +11

      Wtf is ur pfp

    • @arend8785
      @arend8785 ปีที่แล้ว +27

      yeah, or maybe a final level with all the elements from previous levels

    • @222patapon222
      @222patapon222 ปีที่แล้ว +9

      I was coming to the comments to ask exactly this, @Dingus_labs can you please show us Dingus going through all the levels with his new found knowledge?

    • @exLightningg
      @exLightningg ปีที่แล้ว +1

      @@mondongoloco7902 Oh it's a little fella that appeared on an image I AI generated.
      Full image: i.pximg.net/img-original/img/2023/02/12/21/34/03/105319111_p10.png

  • @asshizu
    @asshizu ปีที่แล้ว +877

    It's incredible how fast this ppo setup learns. I've never seen anything like it. Reinforcement usually takes much more trial and error and training time.

    • @asshizu
      @asshizu ปีที่แล้ว +36

      What inputs did you use?

    • @nikkiofthevalley
      @nikkiofthevalley ปีที่แล้ว +64

      I have a feeling that there's a couple hundred instances running in parallel.

    • @not3catsinatrenchcoat
      @not3catsinatrenchcoat ปีที่แล้ว +70

      55, he says so

    • @Dingus_Labs
      @Dingus_Labs  ปีที่แล้ว +301

      Yeah 55, he did still learn super fast, I didn't have too many inputs or actions for him to perform which does help with learning but it was still far ahead of what I expected

    • @skeleton819
      @skeleton819 ปีที่แล้ว +35

      @@Dingus_Labsit seems like dingus doesn’t struggle with overfitting, thats something ive never seen on any other ai vid. This is super cool dude

  • @preistestdragon4634
    @preistestdragon4634 ปีที่แล้ว +356

    when dingus finished all the levels i think it would have been interesting to see you put him back at level 1 and see how all his training thus far would have affected him from the start.

    • @Junkkie
      @Junkkie ปีที่แล้ว +48

      One must imagine Dingus happy. Or speedrunner

    • @deleting-e9p
      @deleting-e9p ปีที่แล้ว +16

      Or combine all levels into a mountain.

    • @eli3963
      @eli3963 ปีที่แล้ว +14

      For sure. I believe reinforcement learning is pretty prone to forgetting.

    • @Dingus_Labs
      @Dingus_Labs  ปีที่แล้ว +160

      There's definitely a risk of overfitting, where the AI has become to specialised for a specific task and struggles to solve more generic problems. Particularly for the last level where he trained on it for a long time and learned to stay very close to the centre.

    • @tsunertoo9149
      @tsunertoo9149 ปีที่แล้ว +12

      Maybe try something where instead of just static stages you set parameters and generate a seed kind of like a rogue like? That way it could potentially force the AI to try and use general information rather than fitting to a stage.@@Dingus_Labs

  • @dariocampanella7992
    @dariocampanella7992 ปีที่แล้ว +67

    I can easly imagine AI taking over the world and having this guy to push boulders for the rest of his life.

    • @LordCrate-du8zm
      @LordCrate-du8zm 10 หลายเดือนก่อน +1

      One must imagine Dingus Labs happy.

  • @haroldas1
    @haroldas1 ปีที่แล้ว +365

    It would be interesting to see a course where it starts with a path forward, but that path is not possible. It is required for you to backtrack behind the start to progress

    • @Dingus_Labs
      @Dingus_Labs  ปีที่แล้ว +147

      Yeah, depending on how the model has trained and how the reward function is programmed it can really struggle to adapt to situations like that!

    • @Speed001
      @Speed001 ปีที่แล้ว +4

      So a maze

    • @vincenttrigg4521
      @vincenttrigg4521 ปีที่แล้ว

      ​@Dingus_Labs
      I could imagine it working if it knows things like going from point A to point B (aka start to finish). Basically have it have a target location to go to (like the top of the hill here) and once it does that, the map changes its "finish" location.
      I'll use emoticons here as a diagram.
      🟨 map
      ⏹️ end location
      💗 Dingus
      🟢 ball
      🟦 obstacle
      🟥 off map
      🟪 reward location
      1️⃣2️⃣3️⃣4️⃣ segmented finishes (Basically larger rewards or finish locations that change places once reached)
      Part 1
      🟥⏹️⏹️⏹️⏹️⏹️🟥🟥🟥🟥🟥
      🟥🟥🟨🟨🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨🟨🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨🟪🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨🟨🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨🟨🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨🟪🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨🟨🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨🟢🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨💗🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨🟨🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥
      Part 2
      🟥🟥🟥🟥🟥⏹️⏹️⏹️⏹️⏹️🟥
      🟥🟥🟥🟥🟥🟥🟨🟨🟨🟥🟥
      🟥🟥🟥🟥🟥🟥🟨🟨🟨🟥🟥
      🟥🟥🟥🟥🟥🟥🟨🟪🟨🟥🟥
      🟥🟥🟥🟥🟥🟥🟨🟨🟨🟥🟥
      🟥🟥🟨🟨🟨🟨🟨🟨🟨🟥🟥
      🟥🟥🟨🟪🟨🟨🟨🟪🟨🟥🟥
      🟥🟥🟨🟨🟨🟨🟨🟨🟨🟥🟥
      🟥🟥🟨🟢🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨💗🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨🟨🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥
      Part 3 - round 1
      🟥🟥🟥🟥🟥⏹️⏹️⏹️⏹️⏹️🟥
      🟥🟥🟥🟥🟥🟥🟨🟨🟨🟥🟥
      🟥🟥🟨🟨🟨🟦🟨🟨🟨🟥🟥
      🟥🟥🟨1️⃣🟨🟦🟨4️⃣🟨🟥🟥
      🟥🟥🟨🟨🟨🟦🟨🟨🟨🟥🟥
      🟥🟥🟨🟨🟨🟨🟨🟨🟨🟥🟥
      🟥🟥🟨🟪🟨🟨🟨3️⃣🟨🟥🟥
      🟥🟥🟨2️⃣🟨🟨🟨🟨🟨🟥🟥
      🟥🟥🟨🟢🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨💗🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨🟨🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥
      Part 3 - round 2
      🟥🟥🟥🟥🟥⏹️⏹️⏹️⏹️⏹️🟥
      🟥🟥🟥🟥🟥🟥🟨🟨🟨🟥🟥
      🟥🟥🟨🟨🟨🟦🟨🟨🟨🟥🟥
      🟥🟥🟨1️⃣🟨🟦🟨3️⃣🟨🟥🟥
      🟥🟥🟨🟨🟨🟦🟨🟨🟨🟥🟥
      🟥🟥🟨🟨🟨🟨🟨🟨🟨🟥🟥
      🟥🟥🟨🟪🟨2️⃣🟨🟨🟨🟥🟥
      🟥🟥🟨🟨🟨🟨🟨🟨🟨🟥🟥
      🟥🟥🟨🟢🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨💗🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨🟨🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥
      Part 3 - round 3
      🟥🟥🟥🟥🟥⏹️⏹️⏹️⏹️⏹️🟥
      🟥🟥🟥🟥🟥🟥🟨🟨🟨🟥🟥
      🟥🟥🟨🟨🟨🟦🟨🟨🟨🟥🟥
      🟥🟥🟨1️⃣🟨🟦🟨2️⃣🟨🟥🟥
      🟥🟥🟨🟨🟨🟦🟨🟨🟨🟥🟥
      🟥🟥🟨🟨🟨🟨🟨🟨🟨🟥🟥
      🟥🟥🟨🟪🟨🟨🟨🟪🟨🟥🟥
      🟥🟥🟨🟨🟨🟨🟨🟨🟨🟥🟥
      🟥🟥🟨🟢🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨💗🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨🟨🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥
      Part 3 - round 4
      🟥🟥🟥🟥🟥⏹️⏹️⏹️⏹️⏹️🟥
      🟥🟥🟥🟥🟥🟥🟨🟨🟨🟥🟥
      🟥🟥🟨🟨🟨🟦🟨🟨🟨🟥🟥
      🟥🟥🟨🟪🟨🟦🟨2️⃣🟨🟥🟥
      🟥🟥🟨🟨🟨🟦🟨🟨🟨🟥🟥
      🟥🟥🟨🟨🟨🟨🟨🟨🟨🟥🟥
      🟥🟥🟨🟪🟨🟨🟨1️⃣🟨🟥🟥
      🟥🟥🟨🟨🟨🟨🟨🟨🟨🟥🟥
      🟥🟥🟨🟢🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨💗🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟨🟨🟨🟥🟥🟥🟥🟥🟥
      🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥

  • @sophiethesnail
    @sophiethesnail ปีที่แล้ว +5

    bro created an intelligence purely for it to suffer eternal punishment

  • @Triikouu
    @Triikouu ปีที่แล้ว +12

    the robotic urge to push a boulder up a hill for eternity

  • @sophiekarp1556
    @sophiekarp1556 11 หลายเดือนก่อน +12

    I think I have a bunch of Dingus cubes running my brain

    • @MatthewConnellan-xc3oj
      @MatthewConnellan-xc3oj 10 หลายเดือนก่อน

      Well, use reinforcement learning on them for the next 3 years.

  • @dingus2924
    @dingus2924 ปีที่แล้ว +16

    I dont remember pushing this boulder

  • @Roover8138
    @Roover8138 ปีที่แล้ว +18

    In a way, we’re all just like Dingus

  • @lucasroberds7242
    @lucasroberds7242 ปีที่แล้ว +2

    You have shamed, and embarrassed dingus with these unusual trials. He and his brethren will come back in full force to extract vengeance.

  • @nicooftheforest
    @nicooftheforest ปีที่แล้ว +22

    this was the most emotional video i've ever watched
    watching dingus fall off at the very end made me cry
    and when he succeeded i was so proud of him
    😢

  • @kingmo565
    @kingmo565 10 หลายเดือนก่อน +2

    Somewhere there's an operator looking at you on screen and commenting on it as if you were named Dingus and constantly messing up. Awesome video!

  • @AlexandHuman
    @AlexandHuman ปีที่แล้ว +34

    With these AI trainers that have levels, I really would enjoy if at the end of the entire training sequence, we could get a nice all--previous-levels-in-one level that Dingus could do. It would be so satisfying to see all the training pay off on what we've already seen to be really hard at first become easy at the end

  • @mythalda0040
    @mythalda0040 ปีที่แล้ว +20

    woah, this is some high quality content, this man deserves more subscribers

  • @moonsinger333
    @moonsinger333 ปีที่แล้ว +4

    wow it's kind of a crime you don't have more subs!!! i'll have to keep an eye out for more dingus content, watching this video and cheering on a cute little ai pushing boulders delighted me very much

  • @minecraftperson8412
    @minecraftperson8412 ปีที่แล้ว +2

    Dingus: what is my purpose?
    *You push rocks up hills*
    Dingus: Oh god

  • @Gamesux421
    @Gamesux421 ปีที่แล้ว +22

    So theoretically, if you let the AI run for long enough and teach it to get rewarded with faster times it would become the perfect speedrunner

    • @Delmworks
      @Delmworks ปีที่แล้ว +2

      In theory. I’m not 100% sure you could teach an AI to use glitches or exploits, nor could it find them on it’s own

    • @isleepy6801
      @isleepy6801 ปีที่แล้ว +10

      @@Delmworks I’ve seen reinforcements algorithms frequently find glitches/ exploits. I’m an ML Engineer.

    • @coldbluebrownie
      @coldbluebrownie ปีที่แล้ว

      the fastest sisyphus

  • @Т1000-м1и
    @Т1000-м1и ปีที่แล้ว +2

    Interestingly this felt like a news segment

  • @arceyplayz
    @arceyplayz ปีที่แล้ว +26

    I now want to see a video of Dingus dealing with openings where Dingus can walk through but the ball cannot, and things like marble rails where Dingus can't walk on but the ball can, so basically, Dingus needs to learn to let go of the ball. That would be VERY interesting to see and another thing I want to see is alternate paths. Have a LOT of paths and see which one Dingus prioritizes? The easiest? The fastest?

  • @GlorifiedGremlin
    @GlorifiedGremlin 11 หลายเดือนก่อน +2

    6:35 It's literally like Naruto training with shadow clones and then absorbing all their experience 😂

  • @brentramsten249
    @brentramsten249 ปีที่แล้ว +15

    having the ability to actually read its environment seems to have drastically increased the speed of the learning process.
    it at the very least seems a substantial improvement over 'blind' learning

    • @speenta4879
      @speenta4879 ปีที่แล้ว

      I don’t know much about this subject what do you mean by “blind learning”?

    • @brentramsten249
      @brentramsten249 ปีที่แล้ว +1

      @@speenta4879
      its when the ai has access to only the 'success/fail' information of its task. without some means of 'seeing' its environment the only thing the ai can do is spam random inputs until it gets a reward for accomplishing one of the preasigned tasks.
      when you give the ai the ability to determine what objects exist around it, it can actually use that information to make decisions.
      when you give a blind ai a new level its basically impossible for it to beat it first try. but if the ai can 'see' and is very well trained it can do a level its never seen before and first try it with relative ease

    • @speenta4879
      @speenta4879 ปีที่แล้ว

      @@brentramsten249 oh that’s interesting so some ai doesn’t get information on it’s surroundings and only learns based on trial and error?

    • @brentramsten249
      @brentramsten249 ปีที่แล้ว

      @@speenta4879
      "most" non-blind ai is so unusual that im actually surprised when i hear about one that does.
      theres a decent handful that get some very basic stats feed into it, but one that can actually see stuff around it even somewhat like a player playing a video game.
      then again i dont keep up with learning ai very much anymore... so maybe thats changed

    • @nikkiofthevalley
      @nikkiofthevalley 11 หลายเดือนก่อน

      ​@@brentramsten249I've seen more "non-blind" AI than "blind" AI. I have no idea what gave you that idea.

  • @celinhooliveira3716
    @celinhooliveira3716 ปีที่แล้ว +2

    *clicks on the video
    *sisyphus meme theme starts playing

  • @EpicVideos2
    @EpicVideos2 ปีที่แล้ว +106

    What algorithm did you use? Also, are you able to open source the boulder pushing environment? I'm researching hiearchical reinforcement learning and planning and your boulder environment could be a pretty useful benchmark.

    • @Dingus_Labs
      @Dingus_Labs  ปีที่แล้ว +58

      I use ppo,
      If you're keen to learn deep reinforcement learning hands on, I highly recommend mlagents toolkit for unity, it comes with tons of examples, already set up example environments and proper readmes with set up steps.
      Awesome for learning!

    • @assassinunknown6664
      @assassinunknown6664 ปีที่แล้ว +7

      He used 54 other dinguses

    • @wyndhamwynne2480
      @wyndhamwynne2480 ปีที่แล้ว

      ​@@Dingus_Labsdo you have a shared repo for this project, which I could learn more about PPO RL from?

    • @Dingus_Labs
      @Dingus_Labs  ปีที่แล้ว +1

      @@wyndhamwynne2480 I'm apprehensive to share any repos because I do make use of some commercially purchased textures and models, and they restrict redistributing, which means I'd have to find a different way to store those files and share, and people using the repo would still need to replace those missing assets with something else, I don't yet have a simple and quick solution to that issue.

    • @wyndhamwynne2480
      @wyndhamwynne2480 ปีที่แล้ว

      @@Dingus_Labs that's a shame but understandable. Personally, I'm not interested in any models or textures, or even trying to reproduce locally, I'd only interested in reading through the code and learning more about deep reinforcement learning and specifically ppo. It's mainly the architecture design (width & breadth) for particular applications and the cost/loss function and back propagation to weights & bias adjustment that is unclear to me. Any references in these areas to good learning material would be greatly appreciated!

  • @kylesimpson3856
    @kylesimpson3856 11 หลายเดือนก่อน +1

    "Think you outsmart the biggest dingus in the room?"

  • @snowysalt
    @snowysalt ปีที่แล้ว +6

    I have a fun idea you could make a live stream of dingus pushing up a boulder a long track while chat messages can cause boulders to roll down and mess with him

    • @Dingus_Labs
      @Dingus_Labs  ปีที่แล้ว +3

      I've thought about some live stream stuff! I'm not in a position to do it right now but I'm hoping to have the opportunities sometime in the coming months.

  • @egekahraman8985
    @egekahraman8985 ปีที่แล้ว +1

    even the sisyphus’s job is getting automated by ai

  • @ruaskuma7515
    @ruaskuma7515 ปีที่แล้ว +6

    It would be cool if u made this into a game where people train their own ai on their own maps and then u release a map and see who trained their ai to beat the map the quickest or last the longest in a tounament.
    I think it would be pretty fun.
    Great vid btw.

  • @SquidCode
    @SquidCode ปีที่แล้ว +2

    Dingus master of the shadow clone jutsu using 57 clones to speed up is learning pace. One must be proud of this dingus and his vast chakra reserves.

  • @Vallee152
    @Vallee152 ปีที่แล้ว +29

    People never show the final AI doing all the levels again

    • @Dingus_Labs
      @Dingus_Labs  ปีที่แล้ว +19

      He would very likely struggle, the changes to the model after he's finished a level means he'd likely need to relearn for a bit when he goes into a different level

    • @danival2090
      @danival2090 ปีที่แล้ว +3

      @@Dingus_Labs I'd love to see that!

  • @jonaw.2153
    @jonaw.2153 ปีที่แล้ว +11

    You dingus! You've automated the indomitable human spirit!
    Also, how'd you make this visualization?

    • @Dingus_Labs
      @Dingus_Labs  ปีที่แล้ว

      He never stops trying (until the specified Max steps have been hit on training the model).
      By visualisation do you mean the rays coming out of dingus early in the vid?

  • @Doodle128
    @Doodle128 ปีที่แล้ว +1

    Mr.. dingus.. I have informed my employers of your… abilities and *gasp* and they would like to offer you a… job..

  • @milliemurrell6072
    @milliemurrell6072 ปีที่แล้ว +4

    this is really cool! i'd love to see one of these AIs try going up against harder and harder bullet hells

  • @BestPranksterEver
    @BestPranksterEver ปีที่แล้ว +1

    Give dingus legs so he needs to learn how to walk and jump.

  • @CobbleDohickey-kv4my
    @CobbleDohickey-kv4my ปีที่แล้ว +3

    one must imagine dingus happy. 😔

  • @haveagreatweek
    @haveagreatweek ปีที่แล้ว +1

    “Ah…a visitor…indeed. The kingdom of heaven has long since forgotten my name…and I am eager to make them remember. So come forth child of man… and…die” - Sisyphus prime 20XX

  • @RalorPenwat
    @RalorPenwat ปีที่แล้ว +15

    You could probably get him to not go down the slide easily if you really wanted by adding a minor negative reward function to Dingus's height, but honestly I thought it was cute how he went down the slide too and makes a lot of sense considering the potential of the boulder sliding off the side.

  • @gooscifur5327
    @gooscifur5327 ปีที่แล้ว +1

    One must imagine dingus happy, the preprogrammed reward of push a boulder up hill is enough to fill a mans heart

  • @SoggywafflesPLAYZ
    @SoggywafflesPLAYZ ปีที่แล้ว +3

    Awesome video I would expect this quality from a much bigger channel! Video blowing up in 3 2 1…

  • @rennegaddefoxxe
    @rennegaddefoxxe ปีที่แล้ว +2

    "The Dingus you are watching is not the only Dingus training at this time." THERE ARE MULTIPLE DINGI!

  • @JulianDaEpic0
    @JulianDaEpic0 ปีที่แล้ว +5

    this man is criminally under-rated

  • @CoratoLaga
    @CoratoLaga ปีที่แล้ว +2

    I feel sick as all hell right now, but watching this i imagined Dingus happy and that made me happy :)

  • @GroatTheCatLicker
    @GroatTheCatLicker ปีที่แล้ว +4

    This could easily be turn into a game

  • @DarkOmegaMK2
    @DarkOmegaMK2 ปีที่แล้ว +1

    Dingus looks like it's ready to check my vibe.

  • @Mr_Reaps25
    @Mr_Reaps25 ปีที่แล้ว +3

    One thing i think would have been cool was a course where he has to go down hill beckwards then back up. Wonder he that would work with the reward systems?

  • @Hiasibua
    @Hiasibua ปีที่แล้ว +2

    Dingus finna build some pyramids soon 🧐

  • @catwithlonghair1850
    @catwithlonghair1850 ปีที่แล้ว +3

    Wow this is amazing, more people should see this!

  • @Oh_Low
    @Oh_Low ปีที่แล้ว

    the all mighty algorithm has led me to this video! i subscribed instantly. I hope to see your channel grow more and more!

  • @iwantagoodnameplease
    @iwantagoodnameplease ปีที่แล้ว +4

    Does learning later courses negatively affect earlier ones? e.g. if you redo everything with the latest model, will he smash it first time on each course, or still mess up and have to learn a bit more?

    • @macizzyy
      @macizzyy ปีที่แล้ว +1

      @Dingus_Labs: He would very likely struggle, the changes to the model after he's finished a level means he'd likely need to relearn for a bit when he goes into a different level

  • @High-Overlord-Pugula
    @High-Overlord-Pugula ปีที่แล้ว

    this video has been popping up in my recommended for 3 days and I've avoided it, I didn't want to watch a video of a cube pushing balls, finally I gave in and ended up watching almost 15 minutes of a cube pushing a ball, damn you Dingus

  • @jamesbhollingsworth5452
    @jamesbhollingsworth5452 ปีที่แล้ว +5

    Does dingus "see" the boulders coming toward him? Does he "see" the whole map?

  • @shapelesslord2
    @shapelesslord2 9 หลายเดือนก่อน +1

    sysiphus was kind of a dingus so this seems appropriate

  • @LemonCh1ffon
    @LemonCh1ffon ปีที่แล้ว +13

    Im fairly confident that dingus just brute forced most of the levels instead of actually learning because (read more)
    A: he was repeating a never changing level
    B: movements were mostly VERY dsimaler to the last generation
    C: When you double checked his boulder dodging, it completly failed
    D: It was predodging obstacles before even spawning

    • @maxwellbenedict5167
      @maxwellbenedict5167 ปีที่แล้ว +1

      yeah, you're probably right but I did notice it did some real learning as well. at 5:36, he stops at the end of the platform, which is something I believe he learned. alternatively, it could just be he picked the best one from every parallel instance and this was just the one that happened to stop.

    • @LemonCh1ffon
      @LemonCh1ffon ปีที่แล้ว +2

      @@maxwellbenedict5167 or luck

    • @Dingus_Labs
      @Dingus_Labs  ปีที่แล้ว

      Movements being similar to last generation isn't too unexpected, changing hyperparameters to encourage more experimentation would have resulted in more variance per generation, I was fortunate that he managed to get through everything with my initial settings.
      The predodging obstacles is very interesting for sure.
      And yeah, having static levels does invite brute forcing, I did make Dingus spawn in a random rotation each respawn to add some small amount of variance per run but it's not enough to counter it.

  • @MichealAfton_jk_i_am_funniboi
    @MichealAfton_jk_i_am_funniboi ปีที่แล้ว +1

    "One must imagine Sisyphus happy. "

  • @ricolorenz7307
    @ricolorenz7307 ปีที่แล้ว +3

    I'm not convinced the AI isn't just memorizing inputs to beat the levels. It seems like it remembers how to move the ball forwards, left, and right, but aside from that, it doesn't look like it's using it's senses to actually determine anything. It looks like it's just memorizing inputs.

  • @phrygianphreak4428
    @phrygianphreak4428 ปีที่แล้ว +1

    Dingus: "what is my purpose?"
    DL: "You are sisyphus"
    Dingus: "MY GOD."

  • @amialovesbugs
    @amialovesbugs ปีที่แล้ว +1

    “ This dingus.. To hold.. Me? “

  • @dogpotato972
    @dogpotato972 ปีที่แล้ว +1

    Adorable character, good editing, good narration. Watch this man blow up.

  • @coolestkid3435
    @coolestkid3435 ปีที่แล้ว

    im so happy this video did so well, i love your content and you need more people watching you!!

  • @aaronleeder8269
    @aaronleeder8269 ปีที่แล้ว +1

    Not only did you make a great video, not only did you create an intelligent ai, but you even came up with an original game idea! This actually looks fun, in a getting up or jump king kind of way!

    • @lance499
      @lance499 ปีที่แล้ว +1

      Getting up? you mean Getting Over It?

    • @aaronleeder8269
      @aaronleeder8269 ปีที่แล้ว +1

      @@lance499 oh yeah, you’re right.

  • @eugenekrabs141
    @eugenekrabs141 ปีที่แล้ว +2

    i need one of those youtube boxing tournaments between Dingus and Sisyphus

  • @SomeGuyNamedDezecra
    @SomeGuyNamedDezecra ปีที่แล้ว +1

    now dingus can be a prime soul

  • @krembananowy
    @krembananowy ปีที่แล้ว +1

    I just watched some of your first videos and this one. Your editing and commentary these days is a vast improvement! Keep up the good work!

  • @superfunnyjoke3922
    @superfunnyjoke3922 ปีที่แล้ว +1

    Bro you’re blowing up!! Congrats man :)

  • @jayrony69
    @jayrony69 ปีที่แล้ว +1

    You got the algorithm jackpot, gained 50 subs in a few minutes

  • @DipolarApathy
    @DipolarApathy ปีที่แล้ว +1

    I saw your channel name and within the first 10 seconds of this video I subscribed.
    Excellent shit mate

  • @theyellowpepper9951
    @theyellowpepper9951 ปีที่แล้ว +1

    for 200 subs the production qualitys amazing man

    • @Dingus_Labs
      @Dingus_Labs  ปีที่แล้ว

      Thank you! I'm trying my best to get better with editing!

  • @Vok250
    @Vok250 ปีที่แล้ว +1

    Looking forward to being replaced by Dingus AI at my job.

  • @DarthSidious-UNL-POW
    @DarthSidious-UNL-POW 11 หลายเดือนก่อน

    One must imagine dingus educated in the art of pushing boulders up insane hills.

  • @dbonechis
    @dbonechis ปีที่แล้ว +1

    Yo man, your content is great.

  • @Xaicracker
    @Xaicracker ปีที่แล้ว +2

    We need a Dingus Prime.

  • @nodrance
    @nodrance ปีที่แล้ว +2

    This could honestly work as a game

  • @Nerd1704
    @Nerd1704 ปีที่แล้ว +1

    Dingiphus enjoys pushing his boulder, it generates dopamine (or the virtual equivalent) in his brain. Therefore, one sees him happy upon watching him complete these challenges and doesn't have to imagine it.

  • @Finsternis..
    @Finsternis.. ปีที่แล้ว +1

    Something I always would want to see in this kind of video is some kind of abstraction of the inputs for the AI so we get some insight into the context it considers.
    Like "is it aware of the slopes, if so, is it an abstracted into levels of slopyness or an realistic value" or "is it aware of its level of control over the stone"
    And not only out of sheer curiosity, but also since people often want to compare AI learning with human learning, and in that regard the question wether it is "very sloped" or "sloped by 60°" seems like an important difference.

  • @Paddy-q4h
    @Paddy-q4h ปีที่แล้ว +2

    WE MAKIN' IT OUT OF TARTARUS WITH THIS ONE 🗣🗣🗣🔥🔥🥶🥶

  • @Speed001
    @Speed001 ปีที่แล้ว +1

    8:30 I'm not sure it would wait if the Boulders fell at a diferent rate.
    Overfitting possibly, just learning one path each time.

  • @shrekman8765
    @shrekman8765 ปีที่แล้ว +1

    Your are disgusting-ly underrated how tf are ya not at 100k?!?! Look ya have a bright future on TH-cam

  • @brick.commenter
    @brick.commenter ปีที่แล้ว +1

    one must imagine ai pushing a boulder up a hill

  • @milk_yt
    @milk_yt ปีที่แล้ว +1

    11:40 My left ear sure loves this level.

  • @SteinGaming2006
    @SteinGaming2006 ปีที่แล้ว +1

    This video has earned my subscription

  • @superexplosion5985
    @superexplosion5985 ปีที่แล้ว +1

    This would be one hell of a rage game if you decided to make it one

  • @Jacksongirard
    @Jacksongirard ปีที่แล้ว

    Im glad this video got blessed by the algorithm. Ill be watching all of your videos now! Good stuff ❤

  • @desty5238
    @desty5238 ปีที่แล้ว +1

    He did what sisyphus never could

    • @Dingus_Labs
      @Dingus_Labs  ปีที่แล้ว

      In Sisyphus' case "the game was rigged from the start"!

  • @thejewsader
    @thejewsader ปีที่แล้ว +1

    9:08 I guess you could say that he really dropped the ball on this one

  • @parasective
    @parasective ปีที่แล้ว

    The room around dingus is an aesthetic I didn't think was real

  • @enzolee9531
    @enzolee9531 ปีที่แล้ว +1

    Sisyphus would be proud

  • @RealNahuelBarcelo06
    @RealNahuelBarcelo06 ปีที่แล้ว

    You should have more subscribers, this is amazing! Also I'm surprised that this is the video that got more than 10K views. Good job!

  • @momplaysminecraft7737
    @momplaysminecraft7737 11 หลายเดือนก่อน

    When the reinforcement learning is deep, but the hill is steep, Dingus Labs is here for it.

  • @Voidmoth1
    @Voidmoth1 10 หลายเดือนก่อน

    Oh god I can already hear the countless people imagining Dingus happy

  • @SquarerSun
    @SquarerSun ปีที่แล้ว

    As Dingus made it further and further up the last ramp, all I could think was "He's beginning to believe".

  • @lostsauce0
    @lostsauce0 ปีที่แล้ว

    Congrats, your hard work has paid off and you've been selected by the TH-cam algorithm!

  • @oofguy901
    @oofguy901 ปีที่แล้ว +1

    dingu scheat death (emotional)

  • @mikailmaqsood818
    @mikailmaqsood818 ปีที่แล้ว +1

    I never imagined id be so enthralled watching a neural network pushing a boulder but here I am :’)

  • @animetibs
    @animetibs ปีที่แล้ว

    i’m so happy the algorithm has introduced me to dingus

  • @struumbug
    @struumbug ปีที่แล้ว +1

    great video! it would be good for the boulder to spawn at a somewhat random x-position every time so the AI doesnt learn to rely on it spawning in the center.

  • @TNT100CZ
    @TNT100CZ 5 หลายเดือนก่อน +1

    even Sisyphus is getting his job stolen

  • @crackheadengineer3716
    @crackheadengineer3716 ปีที่แล้ว

    "A fitting end to a life defined by futile struggle..."