looks like infinite timelines upon eachother.. mesmerizing.
@grifith118415 годин тому
now you gotta build an AI that tries to builds an unbeatable track
@sebastiangustavsson221020 годин тому
This is soo interesting
@tuaigets7723 години тому
Now when I loose on multiplayer games I can blame it on chaos theory.
@soberTrezviy23 години тому
microscopic changes affect so much because you set the landing in the middle of the pipe, this is a point of unstable equilibrium. If you intentionally land slightly to the side, while accelerating towards the middle, then you can decide on the fly how long you need to accelerate and thus compensate the randomness. The trick is to change the tactics to lay all the randomness range inside your controllable range.
@Tehn00bAДень тому
T'is but a pipe dream. Xd
@MPD90День тому
This is art. Beautiful.
@slm6873День тому
Initial conditions and numerical precision
@gdcuaer4076День тому
Does anyone know the genre of the music used in this video?
@Fixti0nДень тому
put....put this guy on Deep Dip!
@mfn1311День тому
Haha just watched a video on the three body problem and chaos theory, and I though this would just be good AI fun but turns out to be very relevant to this as well!
@lokergames7058День тому
wtf Ai mean niagara mesh ?
@SuRReal2kДень тому
22:47 nice homage to wirtual!
@acexrp6288День тому
Amazing job with this. Mammoth effort
@AhimtarHoNДень тому
Incredibly well produced!
@user-pk3yh5dk7zДень тому
This is the best video to understand AI. Just thanks !
@KeithAlumbaugh2 дні тому
Can the AI teach my wife to drive?
@countcampula2 дні тому
Those happy lil cars bouncing on the pipe makes my inner child happy. Bounce bounce
@elijah70762 дні тому
I think taking the AI's best run against yourself is a little unfair. Taking the AI's most average run out of its high number of attempts would be a more fair representation. Once the AI's average run is better than yours, then you've created a monster.
@Varksterable2 дні тому
Truly it's an excellent video; totally enjoyable and a masterclass in both video production and tenacity. But everyone is calling this "AI". But is this yet another misuse/overuse of the term? Is this neural network really intelligent? It demonstrates machine learning of a sort; but it's also very guided learning. Without someone tweaking the parameters and making _intelligent_ decisions on its behalf it was clearly inferior. And I'd argue therefore, not intelligent in its own right. Number crunching, building up large data sets with significant nudges from an intelligent 3rd party, and using those data to drive better doesn't to me show any intelligence. It's just (directed) brute forcing a solution. Most humans (at least those an hour or so of playing TM) would be able to get around the track after only a few tries using visual stimulus and knowledge of control inputs and physics. They would be much slower, but this to me is significantly different from how this machine 'learns' the track. True; those humans have probably spent years learning the skills in completely different contexts. But the point is that they can apply a build up knowledge to come up with solutions to new, unknown problems. That's intelligence. Again; it's a fantastic video, and I've watched it multiple times, completely fascinated an in awe. But I still think "AI" is overly misused in contexts like this. As it increasingly frequently seems to be when people play the "FAKE: It's AI!" card on UKposts shorts that use CGI (not even machine learning). I don't think people really understand what AI is supposed to mean. And that's totally reasonable and expected in a way, because: 1) I don't think AI even exists yet. 2) Not everybody is close enough the technology thrown at it under this name. 3) The philosophical definition of _real_ AI is incredibly difficult. 4) Even machine learning isn't generally understood by _anybody_ . The concept of a neural network and how to set it up for machine learning is. But once it starts it's 'training' I don't think anyone really understands what is actually happening. Just like computers now design even more powerful computers that are somewhat beyond human comprehension. Maybe this has changed in recent years; and I totally admit that it's not an area I have any expertise in. But I have worked with people who do have that expertise, and all of them are very cagey about using the term "AI".
@pockpock63822 дні тому
just an fancy automatic TAS imo
@user-oi2zd9zv5k2 дні тому
Just wondering, do you AI to edit/parse/finish your videos?
@TaraKun2 дні тому
Lihat lah para ai hijau di jalur 3 itu, mereka semua berhamburan. Dan tau apa yang lebih keren dari itu? Ya, mreka semua ai hijau, dan bukan ai merah😅
@iseethebluescreen3 дні тому
i wanted the ai to just 2 wheel perfect balance the first track so badly
@LazieKat3 дні тому
I don't want to point the obvious, but can floating point numbers precision (or lack of) be another effect?
@Baigle13 дні тому
Interesting in regards to cryptography too
@limitbreak29663 дні тому
28:26 finally forces the fucker to slow down a bit and suddenly pure consistency lul. AI was just way too fast at first lul
@limitbreak29663 дні тому
27:50 it’s so confused 😂 it’s like “do… do I go forward?… **is immediately punished carrot wise** no… no i go backward :)”
@limitbreak29663 дні тому
21:05 idk. I don’t feel it random, I feel it’s chaotic. Which means it’s predictable, but just hard to predict
@Pjx19893 дні тому
@joshtm Could your experience be used to train the AI of the new Autonomous Racing League (A2RL)? Looking at the results of the other teams, it looks like you are 5-10 years ahead of them. Is their exercise much harder than yours? Do you think there is much difference in the inputs/outputs?
@lcf343 дні тому
Thank you, this is amazing. Wow!!!
@yoshtm2 дні тому
Thanks!!
@MagnusMcManaman3 дні тому
The way you train AI is good for choosing tactics, but not necessarily strategies. In other words, your way of training ensures that the AI in the next step will choose the best solution, but it does not ensure that the whole series of these steps will be the best possible tactics in the long run, because simply this way of training the AI does not take this into account.
@realcudesnivuk3 дні тому
Ah great! Now make it do deep dip 2
@pamppe03 дні тому
yoyoshi
@blx96703 дні тому
The chaos you see in game is probably cause by floats (floating-point numbers) if they are used to represent values in the game, then it would make sense for the car to behave chaotically.
@Fpl86463 дні тому
The term “AI” is used too lightly now….
@bambiidu38803 дні тому
Wdym
@PhantomSpaceman.3 дні тому
Can you teach the AI to drive on just one pair of its side wheels the entire length of the pipe?
@RazorsharpLT3 дні тому
Why can't the robot repeat the same strategy without consistency? I'll try an answer this before you do: *because it keeps getting rewarded for trying different things*
@RazorsharpLT3 дні тому
You might think "well, that's obvious: that's what this A.I does" At some point if it gets rewarded TOO much for doing "different things" - then it will DO those different things even when it doesn't need to.
@bbrrrrr65534 дні тому
Intéressant, intriguant, étonnant, fascinant, et même émouvant... Quel travail d'immense qualité, merci de tout cœur !
@ferociousfeind85384 дні тому
24:04 (it also seems to be using an analog input with no input noise, i.e. infinite precision too, which I'd call just as important as quick decisions)
@ferociousfeind85384 дні тому
What I've noticed so far (8 minutes in) is that the AI indeed (as you said, yeah) can only change its input 10 times per second. With a game that processes 60 times per second, that leaves a whole 5 frames for something to go wrong for the AI to be unable to correct for. However, I suspect allowing the AI to input 6x more frequently would make training take 6x longer...
@punchster2894 дні тому
USE A SOFTMAX
@ShannonJosephGlomb4 дні тому
Real life AI driving you would win at ukposts.infoTPzBH-7ckO0?si=YEEf2BG8cfsEyg24 ❤❤❤❤❤❤❤
@vxxed86684 дні тому
21:32 I think your memory between inflections is too short for that large maze. From what I could tell it was using C_n and D_n variables to sort of make a map in its memory, based on the states of these variables? If this is correct, then you might need to extend it a tiny bit to allow for more combinations. Maybe then it can learn vertical tracks as well.