ฝัง
- เผยแพร่เมื่อ 4 พ.ย. 2017
- I trained a recurrent neural network to play Mario Kart human-style.
MariFlow Manual & Download: docs.google.com/document/d/1p...
Mushroom Cup: / 183296063
Flower Cup: / 183296268
Star Cup: / 183296400
SethBling Twitter: / sethbling
SethBling Twitch: / sethbling
SethBling Facebook: / sethbling
SethBling Website: sethbling.com
SethBling Shirts: sethbling.spreadshirt.com
Suggest Ideas: / sethblingsuggestions
Music at the end is Cipher by Kevin MacLeod - เกม
Seth is trying to create a brain clone of himself so he can never really die.
+purplebootsgames I'd have this at my funeral as free merchandise for fans of my brain.
Welcome back, SethBling Reincarnation #4 here
SethDOS
One day you will be able to race Seth even though he's deader than a doornail
*THE RIDE NEVER ENDS*
"What is my purpose?"
"You try to mimick how I play in Mario Kart"
"...Oh my god"
mushroom taco lol
Poor lil' robot
That is why machines rose against mankind xD
mushroom taco That is a whole hack of a lot better than serving butter.
IM PICKLE RIIICK!!!!
A year ago I watched your MarI/O video and was exposed for the first time to neural networks. It was because of watching that video that I decided to take machine learning courses at my college. I am now pursuing a career in AI. Thanks so much!
The Modern Shoe ~ 👍
Similar story for me. I was focused on game design but I am switching courses around now to fit a machine learning path.
Rory Williams Wow, I am doing that too
Quick! Someone train it on TAS data!
Kitty40 lol
Whats TAS
Kitty40 you'd think it would work well, but in reality, it would be even more prone to getting confused when seeing unfamiliar situations.
It would just memorize almost the entire tas perfectly, RNN's are very powerful structures.
actually I was going to start working on something like this. I'm going to target SMB3 and see what it can learn.
If you're interested in learning more about neural networks, I highly recommend looking up "3blue1brown" on youtube and watching his videos about neural networks. It made my understanding of neural networks go way up!
Thanks for the recommendation!
LazerLord10 we
Same, I was just about to come down here and make my own comment suggesting the same thing.
For more interesting projects using neural networks I also recommend carykh
LazerLord10 thanks
@ 3:42
"I recorded 15 hours of training data."
Otherwise known as playing the game. xD
Gotta give props to him for having the patience to play a relatively boring game for 15 h.
@@sontapaa11jokulainen94 Can be done in small increments, say 20min one day and 2h the next day maybe 30min the 3rd day etc
@@thisflyingpotato4227 yeah but still playing 15 h of some crappy (for todays standards) racing game is hella boring
... and behind this is a bunch of command blocks!
Don't forget about the armorstands
kek he doesnt do minecraft anymore though
and behind _that_ is an original joke
Behind your comment is where you'll find a mountain of salt.
Minecraftfan4 hes still having a Redstone channel picture though...
Wow, the trade off play idea was pure genius! Did you set it up so you could override the networks commands at any time, or have control alternate back and forth at a regular interval? I love the idea of taking control and guiding the network, like you're a master painter guiding the hand of your apprentice...... so sick!! Amazing work!
I just had it switching at slightly random time intervals, because I didn't trust my reaction time to be fast enough to correct the errors as quickly as I wanted. So I was just always pressing the correct buttons, whether or not I had control (even though it was only recording my button presses when I was in control).
+SethBling I have no idea what either of you said but ok
They're talking about 4:27.
SethBling Nice! So, have you ever considered DefCon? Your content could be very interesting over there.
SethBling I thought that you had programmed it to relinquish inputting command when it detected input from an external controller
*Dope*
*_Nope_*
666 likes original
I've been wanting to get into neural networking just recently so a refresher video of you demonstrating some of the cool things we can do is an awesome inspiration! :D
Good that I watched the 3blue1brown videos so I understood something!
SpektralJo thx
Same! I was like, "I actually know some of these words and the math behind it"
Oh also the sigmoid, weight, layers, etc.
O sht a bro
Same
I'd be interested to see how it would react to a speed runner training it.
You should probably get a github page going if you want to share source code? Much better interface than google docs :)
+orochimarujes
You should probably take a common sense lesson?
Love it. Keep up the good work SethBling!
Finally!!! More neural network videos! Keep it up SethBling, I love this stuff!
Miguel Ballard Agreed! Nothing I find more interesting really... you can apply them to an endless amount of problems!
Currently learning neural networks, and this is gold. Thank you !
this stuff is so incredibly cool! I love these videos!
So glad you finally released the video on this!
These neural network videos are so good. Please make more!
That idea to switch between NN and yourself was pretty clever . I'm often impressed by your creativity man !
Your projects are so cool!
Cipher
So cool man! Great work!
Brilliant, as always. Thanks Seth.
Oh my, man, I love your neural network videos
This is amazing. Well done!
it was fun watching the videos in the background while I was working
This is very cool! If you are looking for something pretty simple to try and tweak this with, adding convolutional layers prior to your LSTM layers seems tailor-made for this type of application. Chase those gold cups :)
This is freaking awesome! Subbed!
As always this is so, so cool. lov u Seth. 👍
I love your content to bits.
Amazing! Keep up the great work.
Thank you Seth - this is a brilliant introduction to NNs!
Really good, I'm personally working on a number recognizer so yeah, good video!
I wonder how good it could get watching TAS runs
Starting to find inspiration to get into this AI and Machine learning world. Awesome! Thanks for sharing!
Great work on the Skynet-Basics ! Keep on with your work
Professor just used this video in our class, super cool stuff.
yesss another seth video
nailed the guess. i was staring ay the bottom left quadrant of gameplay from the start.
This channel has had such a weird progression over the years. I love it
Very cool, just subscribed!
Great video and great job!!!
Great stuff!
I have no idea what's going on, but I'm thoroughly entertained
This was a great explanation! In case you want a more detailed version, 3Blue1Brown currently has a great series on that.
That is some seriously impressive stuff.
The man is back on TH-cam!
Amazing! Thanks for sharing
Super cool video!!
As someone who just started learning Tensorflow. This is awesome!
Jesus fucking christ dude, every video I see of yours is amazing. Love how smart you are my bro, keep up the good work.
Your idea is awesome.
Combine the two systems... I think that would be interesting...
Thats what i was thinking too!
Easier said than done
You mean an LSTM(variant) "trained" via NEAT? That's a good idea that's sadly rarely done
Yes, why 200 neurons in 2 levels? Is that more than enough raw brain material that learning can take place, or can it be optimized further.
Lol you got me with Mr. Electric Mars.
One word - *Astounding*
I am now enamored with the idea of having a tournament where everyone brings their own trained AI and then they compete.
It'd be like an Amiibo tournament in SSB4, but for the Super Nintendo.
This video legitimately scooped a paper by a professor I was working with. "HG Dagger" uses the same idea of having a human take over control of an agent, and was published a year after this video
I got the notification for this video as I opened youtube.
GG
Amazing. As someone who just entered the world of Machine Learning, this video motivates me to become better and better at ML until I am also capable of creating NNs that can perform tasks like this.
lova ya work bro !
Amazing mate
so last year. I did an essay for school on using neural networks for self-driving AI. and it failed miserably. both types of networks failed to go through a basic obstacle course. Spent a month's worth of time coding.
Now I found that every major organization + Sethbling have done it and they make it look easy.
This is actually what I was wandering
Very cool, makes me think of markov chains and cybernetic feedback.
And here I am just watching TH-cam videos. I ain't even mad. Good job. :D
man that was so mind boggling
Thanks for the more in explanation!!!
This sounds like a class project
very nice! I am impressed.
This brilliant!
Self driving cars are also the future of video games
Dude this is epic
0:57 I knew it. I put my finger to the screen when I saw him skid around like that.
This is the ultimate turing test!!
I just love SethBling's neutral voice xD
Wow..... mind BLOWN 💣
Oh man, I've worked with neural networks and classification with statistical information before. Seeing stuff like this make me feel like my experience is equivalent to handing a monkey a picture of a corvette and expecting him to assemble one.
Just like giant_neural_network pointed out, I had to comment about the geniality of the trade off play. Amazing idea!
Would be cool if we could get more interesting AI in games, using tech like this.
play against a bot that is trained by your own style of playing, that would be pretty awesome. :)
Imagine training a RNN to fight enemies like you do for a whole JRPG.
Then surprise, there's a secret dungeon where you enemy is a "clone" of your playstyle.
That would be beyond amazing.
I like how this channel went from Minecraft videos to neural networks videos
Being in calculus now your videos make sm more sense
Great idea!
In feed forward the inputs are actual between 0 and 1 in most cases, to fit in with the sigmoids in the later layers :)
These videos are great ^-^
Tried the last MariIO. That was the best open source ML project I had tried on.
amazing!
i bet the best part was actually playing and recording your gameplay.
So instead of learning from itself MariFlow learns from you? Neat
Definitely the best Minecraft youtuber out there
Google DeepMind has AlphaGo
Elon Musk has OpenAI
SethBling has MariFlow and MarI/O
Connor smart
*google deepmind has alphazero.
They now have AI for chess too and it beat Stockfish 20+ times (Stockfish is one of the strongest engine on chess, rated 3300+)
leela zero is an open source version around 2400~ you can play
*Elon Musk has left the chat*
0:11 BEST joke ever, you got my like bro !
How much armor stands did it take
Great Video
This is sick
Seth is a genius
*Buddon intensifies*
We seriously need a neural network mario kart tournament.
Did you consider using a generative adversarial network to generate more training data for the RNN? It would be interesting to compare the effect of that on the performance to the effect of using your trade off play idea.
Thank for making this open source
Holy fuck, what next, fully functioning Hal 9000 and GLaDOS? Seth, you're just making the world 1 step closer to being overtaken by robots, LOL. Loving these projects, keep up the good work! You need a patreon