Tap to unmute

How to train simple AIs to balance a double pendulum

แชร์
ฝัง
  • เผยแพร่เมื่อ 4 มิ.ย. 2024
  • Previous video: • How to train simple AIs
    XPBD article: matthias-research.github.io/p...
    Github github.com/johnBuffer/Pendulu...
    Music used (in order of appearance):
    - Winterbeams by Diffie Bosman
    - Empyrean by Dear Gravity (4000 pendulums part)
    - Poison Message by Man with Roses
    - The Endurance by C.K. Martin
  • วิทยาศาสตร์และเทคโนโลยี

ความคิดเห็น • 644

  • @HolySerega
    @HolySerega หลายเดือนก่อน +1202

    Imagine training for 46 years and the god says, "naaaah, you wiggle too much"

    • @maxim_ml
      @maxim_ml หลายเดือนก่อน +22

      i know RIGHT

    • @ianweckhorst3200
      @ianweckhorst3200 หลายเดือนก่อน +39

      I feel like the evolution of quick oscillations was frankly quite cool and made sense with such a chaotic system

    • @AA-cg1wm
      @AA-cg1wm หลายเดือนก่อน +22

      "but, but i did the task sir!"
      *nope echoes in distance*

    • @mr_b_hhc
      @mr_b_hhc หลายเดือนก่อน

      I would argue with him that in such a case "well, you made me so are at fault". Unless of course I had be given free will?

    • @user-xm7vu9ql8n
      @user-xm7vu9ql8n 27 วันที่ผ่านมา

      😂😂😂😂😂😂

  • @marklondon9004
    @marklondon9004 หลายเดือนก่อน +1167

    I went from "Only a fool thinks he can balance a double pendulum" to "Praise the lord, he walked on water!"

    • @extremechimpout
      @extremechimpout หลายเดือนก่อน +18

      irl it's impossible so you were right

    • @MrHardzio4Fun
      @MrHardzio4Fun หลายเดือนก่อน +79

      ​​​​@@extremechimpoutSo your claim is that all YT videos with robots doing that are fake? Even with triple ones.
      In real life it does not wobble as much, everything has friction. It's actually easier irl.

    • @extremechimpout
      @extremechimpout หลายเดือนก่อน +2

      @@MrHardzio4Fun I looked there are no such videos

    • @mapron1
      @mapron1 หลายเดือนก่อน +25

      @@extremechimpout I looked there are many of those video, even quadruple.

    • @MrHardzio4Fun
      @MrHardzio4Fun หลายเดือนก่อน +25

      ​@@extremechimpoutLook harder.

  • @msx80
    @msx80 หลายเดือนก่อน +541

    The idea of starting with lower gravity and higher friction is simply genius

    • @research417
      @research417 หลายเดือนก่อน +39

      Yeah he immediately solved a problem that even that professional research paper struggled with, and it intuitively makes perfect sense how the learning can transfer over from the simpler problem to the more complex problem. Goes to show that sometimes all you need is to just reframe the problem.

    • @CliffHanger-fg6uy
      @CliffHanger-fg6uy หลายเดือนก่อน

      @@research417If you google it, you’ll find that it was a project report from an undergraduate machine learning course…
      It’s still a cool approach, though.

    • @reyariass
      @reyariass หลายเดือนก่อน +8

      For real, when I saw the research paper I thought Pezzz was going to show something else because the “professionals” said it was not possible. It’s amazing how it just took a small change to make it work. Great work pezzz

    • @oko3717
      @oko3717 25 วันที่ผ่านมา

      ingenious

    • @joaosousapinto3614
      @joaosousapinto3614 20 วันที่ผ่านมา +3

      It’s common in the field of reinforcement learning. It’s called curriculum learning.

  • @Geosquare8128
    @Geosquare8128 หลายเดือนก่อน +382

    the agent UI/visualization, the training graph hyper parameter view, the movitated loss function explanations.. all so well done wow

    • @PezzzasWork
      @PezzzasWork  หลายเดือนก่อน +29

      Thank you!

    • @gus2603
      @gus2603 หลายเดือนก่อน +6

      ​@@PezzzasWorkcan you make a video doing those?

    • @yalnisinfo
      @yalnisinfo หลายเดือนก่อน

      @@gus2603absolutely support this 🎉, i want to avoid looking at numbers as much as possible.

    • @soumyodiptanath2917
      @soumyodiptanath2917 หลายเดือนก่อน

      Is it made using Python?

    • @PezzzasWork
      @PezzzasWork  หลายเดือนก่อน +10

      Everything is made using C++

  • @CriticalMonkey623
    @CriticalMonkey623 หลายเดือนก่อน +942

    My toxic trait is believing that I would be extremely good at balancing a double pendulum with zero practice.

    • @PezzzasWork
      @PezzzasWork  หลายเดือนก่อน +167

      That would be very impressive :D

    • @CriticalMonkey623
      @CriticalMonkey623 หลายเดือนก่อน +74

      @@PezzzasWork Your videos are always so clean and well put together. I've finished the video now and the final solution you came up with is great. The idea to incrementally ramp up the difficulty was a stroke of genius that felt so obvious after you said it. Great work showing that paper what's possible!

    • @smileyp4535
      @smileyp4535 หลายเดือนก่อน +7

      @@CriticalMonkey623 yeah maybe if you could somehow do that irl you'd actually be able to do a double pendulum balance

    • @anonanon6596
      @anonanon6596 หลายเดือนก่อน +8

      If single pendulum is like balancing a broomstick on your finger, then double is like balancing a broom stick on top of another broomstick, on top of your finger. Suddenly it does not seem so easy.

    • @adora_was_taken
      @adora_was_taken หลายเดือนก่อน +1

      @@anonanon6596 nah i could do it

  • @xwxwvyz1
    @xwxwvyz1 หลายเดือนก่อน +204

    it was both surprising and entertaining to see the AI doing the blender move whenever the pendulum drops like a kid throwing tantrums

    • @daniel.lupton
      @daniel.lupton หลายเดือนก่อน +5

      It's less "doing a move" and more potential energy being converted into kinetic. If the pendulum falls from its highest position it will be moving fast without a correction.
      Since it is more stable lower down, it will tend to spend more time rapidly spinning below the axis that slowly spinning above it, unless intervened.
      And finally, the AI, like any control system has a maximum frequency/speed it can manage, above which it breaks down and essentially become random input.
      So while the AI might be able to take the slow pendulum and balance it up high, if it then falls, it might not have the skill needed to recover. So every failure mode leads to a rapidly spinning "blender".

    • @xwxwvyz1
      @xwxwvyz1 หลายเดือนก่อน

      @@daniel.lupton i know how the doube pendulum works and i also know the situation is either what you said or the AI gaining reward through some loophole in the reward system since its technically over the parameters once every loop (thought this because blenders became less of a problem with each added condition)
      But i just wanted to make a visual comparison between malfunctions of AI and toddler brains where they start giving seemingly nonsensical inputs to solve their impossible problems (which is your statement anyways)

    • @daniel.lupton
      @daniel.lupton หลายเดือนก่อน

      @@xwxwvyz1 Yeah sorry I didn't mean to imply you didn't understand it. I think I was just looking for an excuse to explain why the blender thing happens.

  • @jonathanhelgesen8800
    @jonathanhelgesen8800 หลายเดือนก่อน +201

    The idea of gradually increasing gravity and reducing friction is just genius! Would be interesting to see if this method also would work for a triple pendulum 🤔

    • @andrewferguson6901
      @andrewferguson6901 หลายเดือนก่อน +11

      boyo do i have some news for you
      "World's first video of 56 transition controls for a triple inverted pendulum : 3-body problem"

    • @ThePyrosirys
      @ThePyrosirys หลายเดือนก่อน +9

      @@andrewferguson6901 That video is not using an AI controller, it's a controller calculated from methods found in control theory.

    • @Pockeywn
      @Pockeywn หลายเดือนก่อน

      @@andrewferguson6901lmao i found the video and apparently i already started it at some point

    • @Gwarks337
      @Gwarks337 หลายเดือนก่อน

      Seems like engineers doing that for years th-cam.com/video/cyN-CRNrb3E/w-d-xo.html this one some years

    • @dumb8671
      @dumb8671 หลายเดือนก่อน

      Woah there buddy thats enough

  • @o-..-
    @o-..- หลายเดือนก่อน +176

    I didnt even think that it would be possible, wow, also nice editing and everything is just put in a way that makes the video really enjoyable 🎉

    • @PezzzasWork
      @PezzzasWork  หลายเดือนก่อน +11

      Thank you very much!

    • @mage3690
      @mage3690 หลายเดือนก่อน

      All AI are essentially just function emulators.

    • @CliffHanger-fg6uy
      @CliffHanger-fg6uy หลายเดือนก่อน

      @@PezzzasWorkDefinitely a cool video.
      If you end up doing a follow-up, here are a couple of things I would like to see (as a control theorist):
      - test with random disturbances that also take place during the swing-up control. You could also think of this as adding a little noise to the inputs of the NN. I think you would have to include this in the training as the swing-up didn’t look like it would tolerate any sort of disturbance.
      - It would be nice if you gave the audience the ratio between maximum acceleration and gravity used.
      - I definitely agree that it makes more sense to use acceleration as the control input.

    • @CliffHanger-fg6uy
      @CliffHanger-fg6uy หลายเดือนก่อน

      @@PezzzasWorkalso, I think that “article” you mention on NN-based control of a double pendulum is just a project report from an undergraduate ML course.
      Finally, if you’re unable to make your NN solution robust to disturbances or noise during the swing-up, you could use the ML approach for the “feed-forward” control, basically as a planned trajectory and add conventional control theory on top to stabilize the trajectory w.r.t. noise/disturbances.

  • @amzogm8749
    @amzogm8749 หลายเดือนก่อน +108

    The next step is teaching an AI to balance a million pendulums.
    Keep up the great work, it's both educational and entertaining!

    • @saferugdev8975
      @saferugdev8975 หลายเดือนก่อน +11

      we just need a million dyson spheres so the model training doesnt take 100 years

    • @wanfuse
      @wanfuse หลายเดือนก่อน

      nah dont need a million just the magic number 7

    • @strecher777
      @strecher777 หลายเดือนก่อน +13

      Do you mean balancing a rope? 😂

    • @wanfuse
      @wanfuse หลายเดือนก่อน

      @@strecher777 no but I will share it when the time is best!

    • @caballeronocturno124
      @caballeronocturno124 หลายเดือนก่อน

      We need to balance the n-pendulum

  • @makebreakrepeat
    @makebreakrepeat หลายเดือนก่อน +38

    Your videos are always a delightful blend of programming, puzzles, science and philosophy. Thank you for making YT a better place

    • @PezzzasWork
      @PezzzasWork  หลายเดือนก่อน +7

      Thank you very much!

  • @richardcoppin5332
    @richardcoppin5332 หลายเดือนก่อน +26

    👌🏼 Magnificent.
    It was really great idea to use air friction as the simplifying factor.
    I world love to see the cost of work in the evaluation function.

  • @isaacbutler4262
    @isaacbutler4262 หลายเดือนก่อน +72

    Very nice!, I really enjoyed the first video, it helped me create my own NN. Keep up the good work

    • @PezzzasWork
      @PezzzasWork  หลายเดือนก่อน +6

      Thank you!

  • @gm4984
    @gm4984 หลายเดือนก่อน +25

    Love this approach of setting up an easier environment, for the ai to learn from and slowly increasing the difficulty. I would also love to see how you are going to explore this aspect in the future :D

  • @triplezgames3882
    @triplezgames3882 หลายเดือนก่อน +8

    It's so interesting how friction and low gravity helped the AI learn. It's like humans practicing something complex in simpler variant, because trying to do something like balancing a double pendulum would completely overwhelm us too having no idea about how you would even start counteracting the imbalances

  • @janmuntsiglesias577
    @janmuntsiglesias577 หลายเดือนก่อน +41

    keep up making this content!

    • @PezzzasWork
      @PezzzasWork  หลายเดือนก่อน +16

      I will try :)

  • @kevintrigg3707
    @kevintrigg3707 หลายเดือนก่อน +12

    the progressive difficulty was an amazing training tool! very well put together video

  • @davidamatolondriz8512
    @davidamatolondriz8512 22 วันที่ผ่านมา +3

    Congrats on the video man! Literally the best 20min in TH-cam since many time ago!

  • @vibaj16
    @vibaj16 หลายเดือนก่อน +5

    It's amazing how you go above and beyond. After that first working solution, I would've been really proud of myself and be done with it, but you just make it better and better.

  • @martinfisker7438
    @martinfisker7438 หลายเดือนก่อน +3

    That pendulum rainbow animation is straight art

  • @alxklgn364
    @alxklgn364 หลายเดือนก่อน +6

    The editing and the feedback UI are brilliant. Cheers, Pez.

  • @SiddhantSharma181
    @SiddhantSharma181 18 วันที่ผ่านมา

    I like your idea of starting with a simpler problem and gradually increasing the difficulty

  • @leggyjorington3960
    @leggyjorington3960 หลายเดือนก่อน +1

    The UI and graphs for this video look amazing! Keep up the good work!

  • @bmdsch1320
    @bmdsch1320 หลายเดือนก่อน

    This is amazing! I have been waiting for this second part and its finally here! Its amazing that you can produce a video with such a good quality and informative in such short time!

  • @K0rck
    @K0rck หลายเดือนก่อน

    Amazing work. It was _really_ engenius the way you break up the problem for the evolution algorithm! And the interface you put together to demonstrate the work just adds the cherry on top of it. Keep up the great work, I'm looking forward for the next one!

  • @mzg147
    @mzg147 หลายเดือนก่อน +2

    love the visuals, the clean colored borders... perfect!

  • @naijii
    @naijii หลายเดือนก่อน +2

    The UI is incredible and everything is very well presented!

  • @kellymoses8566
    @kellymoses8566 หลายเดือนก่อน +4

    starting easy and gradually increasing the difficulty is a very clever idea.

  • @lanha3385
    @lanha3385 หลายเดือนก่อน +1

    You made it absolutely wonderous and intrigued interest to the notion of chaos. Well done

  • @eelcohoogendoorn8044
    @eelcohoogendoorn8044 หลายเดือนก่อน +4

    Really nice! I liked the velocity-commanded version better than the acceleration commanded one. In many practical cases that is also found to matter; 'in theory' equivalent neural networks should exist but controlling acceleration does bias towards smooth accelerations indeed. In practice a motor controller often has an internal PID control loop; so commanding a velocity (and having that quickly realized, up to physical constraints on acceleration; something like min(max_motor_accel, velocity_error/dt)) isnt necessarily an unnatural choice. It still allows for spiky torques to be learned where they are required in a natural manner.

  • @liamseanalbarel-hepburn6436
    @liamseanalbarel-hepburn6436 หลายเดือนก่อน

    I haven't worked with neural networks before, but you definitely inspired me to start looking into it and giving it a shot. Well done with your solution, and good work for not giving up!

  • @phoenixxofficial
    @phoenixxofficial หลายเดือนก่อน +1

    Your work never ceases to amaze me

  • @stoobidthing
    @stoobidthing หลายเดือนก่อน +2

    Amazing video as always, I love the visuals on this one! Greetings from Paraguay 🇵🇾

  • @BORCHLEO
    @BORCHLEO หลายเดือนก่อน

    this is such an amazing visualization and intersection between so many beautiful forms of mathematics. thank you for this @Pezzza's Work

  • @poketopa1234
    @poketopa1234 12 วันที่ผ่านมา

    Seriously such a great video. I love the curriculum learning approach!

  • @auds9738
    @auds9738 18 วันที่ผ่านมา +1

    The double pendulum paths at 3:20 should be made into a loading screen. I could stare at that for hours

  • @TeamDman
    @TeamDman หลายเดือนก่อน +1

    I'm in love with the interface you designed!

  • @AA-cg1wm
    @AA-cg1wm หลายเดือนก่อน +1

    I'm currently making my own neural network and your videos really helped me understand the concepts and mechanisms of this project

  • @madmanmax120
    @madmanmax120 หลายเดือนก่อน +49

    Triple pendulum when?

    • @themoran2
      @themoran2 หลายเดือนก่อน +9

      Look up "World's first video of 56 transition controls for a triple inverted pendulum". It's the world's first video of 56 transition controls for a triple inverted pendulum.

    • @ccost
      @ccost หลายเดือนก่อน

      @@themoran2 wow

    • @Thomas-ko1nf
      @Thomas-ko1nf หลายเดือนก่อน

      @@themoran2 It can't balance it as long and consistently as this video's double pendulum. Seeing the AI balance it for much longer than 15 seconds would be nice.
      It's still really impressive though and I was on the edge of my seat seeing a triple pendulum being balanced.

    • @themoran2
      @themoran2 หลายเดือนก่อน

      @@Thomas-ko1nf Seeing as how it's a triple pendulum balanced in real life, it's hardly surprising an AI in a simulated environment is more stable.
      Then again, it's the world's first video of 56 transition controls for a triple inverted pendulum, not the world's first video of a triple pendulum perpetual balancing act.

    • @ThePyrosirys
      @ThePyrosirys หลายเดือนก่อน

      @@themoran2 That video is not using an AI. It's from a lab researching control theory. They developped their own method based on control theory.

  • @user-fh7tg3gf5p
    @user-fh7tg3gf5p 17 วันที่ผ่านมา

    Genius. A perfect use case to illustrate what is the special ability of a neural network.

  • @ghomeyshi7
    @ghomeyshi7 หลายเดือนก่อน +5

    give this man a Nobel prize! respect!

  • @Syntax753
    @Syntax753 12 วันที่ผ่านมา

    First time I stumbled across one of your videos and this is fantastic work! Loved it. Channel subscribed!

  • @shadowcrafter01
    @shadowcrafter01 หลายเดือนก่อน

    Awesome! I've been looking forward to this video since I saw the first one. Did not disappoint

  • @greatwall2003
    @greatwall2003 13 วันที่ผ่านมา

    Great video and fantastic visualizations.

  • @ivocanevo
    @ivocanevo หลายเดือนก่อน +1

    Great video. I love watching the refinements. Human and AI learning together.

  • @mathewgriffiths1870
    @mathewgriffiths1870 หลายเดือนก่อน +1

    This is incredible, such amazing work

  • @99totof99
    @99totof99 หลายเดือนก่อน +1

    Wonderful, you have mastered the art of getting what you want from a neural network!

  • @amzogm8749
    @amzogm8749 หลายเดือนก่อน

    This video is simply fascinating! Seeing how an AI can learn to balance a double pendulum is truly impressive. The explanations are clear, and the visuals are very well done, making the subject both understandable and captivating. I especially enjoyed the demonstration with different weights, and it made me want to try creating my own AI to tackle this challenge. Keep producing such inspiring and educational content, it's a real pleasure to watch!

  • @fwenny
    @fwenny หลายเดือนก่อน +1

    loving the visuals, great video!!

  • @Alayric
    @Alayric หลายเดือนก่อน +2

    Love your ideas and visuals! 🥰

  • @purrzival
    @purrzival หลายเดือนก่อน +1

    This video is so beautiful, great work!

  • @DjDoGGoD
    @DjDoGGoD หลายเดือนก่อน

    Really amazing implementation! The first moment I saw the jerk movements I immediately blamed floats. I was very satisfied when you confirmed it, and decided to switch to doubles, as I was screaming at my monitor. :D

  • @brandoncanfield1725
    @brandoncanfield1725 หลายเดือนก่อน +1

    Beautiful visualizations!

  • @wanfuse
    @wanfuse หลายเดือนก่อน +1

    fantastic! this has so many uses! hope you publish code soon! I have a few ideas what to use it for! I worked for a brief time on this exact problem!

  • @srijanraghavula
    @srijanraghavula 25 วันที่ผ่านมา

    Loved the video, the visualizations, the breakdown and the thought of using not python for everything is whats impressive, immediate sub, hope ill learn how to do this stuff

  • @raulgalets
    @raulgalets หลายเดือนก่อน +4

    the poor guy trained for 46 years, stuck inside the matrix and you said there still room for improvement...

  • @SuperElephant
    @SuperElephant หลายเดือนก่อน +1

    Amazing content would be an extreme understatement.

  • @chrizzzly_hh
    @chrizzzly_hh หลายเดือนก่อน

    Really great video and visualisation. Please add some tests next for pendulum setups that are already in motion to see if it can also stabilize these and not only from resting position. This will be fun!

  • @olliecook1982
    @olliecook1982 หลายเดือนก่อน

    Awesome video! Really shows the complexity in tasks like this, and brings into light the massive challenge of doing this in real life with double and tripple pendulums. I wonder how they managed to get such good control!
    I also find it very interesting how it hits a wall every once in a while than makes 1 small change and just doubles it performance. Thats really interesting!

  • @M_1024
    @M_1024 หลายเดือนก่อน +1

    Increasing the difficulty is a cery good approach, if I ever make a neural network I will probably try it.

  • @dashs2597
    @dashs2597 หลายเดือนก่อน

    Incredible work!! Amazing video!

  • @BendoubaAbdessalem
    @BendoubaAbdessalem หลายเดือนก่อน +2

    you should've add to the score function how are the three points are aligned to avoid exploids such ase the last solution you showed us, also i think that we would like to see the result of the training method of controling the acceleration using the last score function when you was still giving the ai control over speed of the cart not the acceleration, and in the end it was a good video, and it was pretty informative and entertaining in the same time!

  • @rewolfer
    @rewolfer หลายเดือนก่อน

    The idea to increase difficulty was so good. Loved watching it go through periods of great success and fast difficulty increasing.

  • @AE_Sub
    @AE_Sub หลายเดือนก่อน +2

    This is the kind of top tier content youtube was made for!

  • @Maxime2bleau
    @Maxime2bleau 29 วันที่ผ่านมา +1

    I love the interface, great video!!

  • @BCannTV
    @BCannTV หลายเดือนก่อน +2

    Buddy graduated with a phd at 17. Subbed earned.

  • @adem0s687
    @adem0s687 หลายเดือนก่อน

    I just LOVE your interface

  • @sbstndbs
    @sbstndbs หลายเดือนก่อน

    That's very great ! Even if the numerical scheme can hide some dissipation, it is the same for a near-perfect physical system.

  • @ChristofFritz
    @ChristofFritz หลายเดือนก่อน

    Ok, that's hella impressive. I fondly remember visiting "Hannover Messe" with my parents. A convention with a lot of technical stuff. There was a booth where they had a pendulum with a flywheel on the end that automatically uprighted itself and balanced after that. It's stuff like that and what you do here that inspires young people to make stuff like that. Thank you! (And now build a machine IRL that replicates the double pendulum simulation and is controlled by the neural net you trained in the simulation :D)

  • @quinxx12
    @quinxx12 หลายเดือนก่อน

    Such a beautiful project!

  • @EchoPrograms
    @EchoPrograms หลายเดือนก่อน

    Just finished my first implementation of a standard nn with back propagation. I'm 16, so it took a bit, but I'm proud of it. Right now i have it fitting a given function, but it is pretty versatile.

  • @TheLazyGamer42
    @TheLazyGamer42 15 ชั่วโมงที่ผ่านมา

    SUCH ELEGANT SOLUTION

  • @iainmackenzieUK
    @iainmackenzieUK 22 วันที่ผ่านมา

    I laughed at the end when you said "rudimentary" algorithm :)
    Anyhow - Loved this journey with you. Really fascinating. Thanks for sharing (Seems like you have over-come Loki...)

  • @anstropleuton
    @anstropleuton หลายเดือนก่อน

    i CAN spend hours watching 4000 pendulum trajectories that form moving geometry. It's just amazing!

  • @kaylor87
    @kaylor87 25 วันที่ผ่านมา

    I've been obsessed with double pendulums for a long time now, I absolutely loved this video. I honestly started the video thinking it would be impossible to balance.

  • @aw_dev
    @aw_dev หลายเดือนก่อน

    Watched the first video, was amazing. Watching this. Hopefully it's even better

  • @NaviaryMusic
    @NaviaryMusic หลายเดือนก่อน

    To give it a greater intuition for how to recover the pendulums from any chaotic state, you could start each simulation with some applied random motion, instead of hanging dead center.

  • @bareakon
    @bareakon หลายเดือนก่อน

    Petition for a 10-hour version of those 4000 pendulum trajectories to chill out to.

  • @Alnakera
    @Alnakera 22 วันที่ผ่านมา

    We need a 10 hour version of the double pendulum trajectory.

  • @bdcoller
    @bdcoller 11 วันที่ผ่านมา

    Technically fascinating, and aesthetically beautiful. Thanks.

    • @PezzzasWork
      @PezzzasWork  11 วันที่ผ่านมา

      Thank you!

  • @Soulergonote
    @Soulergonote หลายเดือนก่อน

    Honestly I thought it would be impossible, you're a real beast !

  • @TheMiczu
    @TheMiczu หลายเดือนก่อน

    Amazing video, gives great insight how to make AI tackle seemingly impossible task.

  • @Dryfee
    @Dryfee หลายเดือนก่อน

    This video is truly beautiful. And interesting too!

  • @Kingdumkey
    @Kingdumkey หลายเดือนก่อน +1

    Just subscribed. You're a genius

  • @lyuboslavilov
    @lyuboslavilov หลายเดือนก่อน

    Starting from easy conditions and gradually making them complex is simply a stroke of genius! I bet this will be a thing in the near future. You should write a paper

  • @lumi2030
    @lumi2030 หลายเดือนก่อน +1

    phenomenal video

  • @VivienLEGER
    @VivienLEGER หลายเดือนก่อน

    as AI most generaly does not impress me, your work and dedication does. also i love the attention to details like graphics, that s truly amazing!

  • @apia46
    @apia46 10 วันที่ผ่านมา

    those graphs are so cool

  • @moonyl5341
    @moonyl5341 หลายเดือนก่อน +8

    triple pendulum?

  • @Radu
    @Radu หลายเดือนก่อน

    Amazing work :-) I will send this to my students in a couple of years when I'll teach intelligent automation.

  • @Pockeywn
    @Pockeywn หลายเดือนก่อน

    its interesting that in the final result you can so clearly see oscillation at two different frequencies in the output velocity thats cool

  • @Mega-wt9do
    @Mega-wt9do หลายเดือนก่อน +1

    Yess! I was waiting for this video :D

  • @michabuijs2095
    @michabuijs2095 หลายเดือนก่อน

    Man I love this content, I am young and want to know more about this, thank you!

  • @sophiophile
    @sophiophile 19 วันที่ผ่านมา

    Great use of curriculum learning.

  • @Konami9999
    @Konami9999 หลายเดือนก่อน

    beautiful vid! keep up the good work. subbed

  • @axeldaval3410
    @axeldaval3410 หลายเดือนก่อน +1

    mad respect, whole scientist team can get your interview to update the study 😂

  • @imperfectclark
    @imperfectclark หลายเดือนก่อน

    This video is beyond impressive 🤯

  • @rickybloss8537
    @rickybloss8537 หลายเดือนก่อน

    Very impressive. Super useful for my work.

  • @adambkehl
    @adambkehl หลายเดือนก่อน

    WOW! New favorite video of yours

  • @zarkha_
    @zarkha_ หลายเดือนก่อน

    J'attendais cette vidéo avec impatience !!

  • @furbyfubar
    @furbyfubar 25 วันที่ผ่านมา +1

    I feel like you now should write the scientific paper on this. Going from "This problem is yet to be solved" to "I solved it with about 2 hours of training for my model" is huge progress!