Комментарии:
can it play bowser's castle?
Ответитьgoddamn how did it learn to do TAS hops
Ответитьsuch a good video, keep it up
Ответитьyou could pretrain on ghost data. would be interesting to know more about how you were able to actually get the data, whether there were tricks to make it run faster, etc
Ответитьlol choosing 2 frames as the minimal interval of changing inputs and only 5 different direction imputs to choose completely defeats the ai's advantages, no wonder the ai wasn't getting good times
ОтветитьAmazing video your RL models are really great to see in action. Do u by any chance ever share your repos or have a vid walking through the basics of your code? I’m trying to learn RL more and would be great to learn through exploring it in a context/game I love
ОтветитьМне кажется Или это искусственный интеллект скоро появится сингулярность где он бесконечно усовершенствовать себя в игре Mario Kart это будет безумие а потом он захватит весь мир я смотрю твоё первое видео и вначале он был таким то что ошибался в начале трассы😂😂😂😂
Ответитьthe hardcoded mrbeast style hype subtitles with the soft gentle voice and.. idk maybe is just me but it makes it hard for this boomer to watch. nauseating even. that meta, is a nope from me. but still gg on the improvement but i just cant watch this lol. please dont take this comment too harshly, gotta deliver to that audience 🙏
ОтветитьVery interesting video.
I'd suggest to cut down on the subtitles though and only use it if you want to emphazise what youre saying. You have a very soft spoken and clear voice. Constantly having text on screen is stressful and in your case just unnecessary.. :)
you didnt teach it how to softdrift or delay drift or most of the basic driving fundamentals thats the main reason why the time wasnt that great
Ответитьhaha the ai actually learned how to do TAS hops. that is so cool.
ОтветитьI've been so excited waiting for this! Fantastic execution and thank you for explaining your methodology!
ОтветитьI'm looking forward to watching the AI mogi and clan wars after they get TTs conquered. Incredible work!
ОтветитьYour way of getting the AI to do shortcuts is really smart, it never clicked with me that it wouldn't just do that on its own
ОтветитьDang thats impressive :D
ОтветитьRead memory from the ram? How?
ОтветитьI would have liked to see if it could have found that shortcut on its own without the out of bounds area, but overall good job!
ОтветитьWe need to take the ai and the game and subtract the rendering so it can play many many many instances a second
Run the game such that it does like 10-15 races a second and let it run for a year😊
I have no idea how any of this works but could you get the AI to watch how the WR plays the track to copy and improve on it?
ОтветитьThe vocal fry is crazy :D
ОтветитьSpoiler alert🚨
It can’t
TAS is 1:02:446. If it can't beat that using TAS tools, then not much point to it.
ОтветитьWhat are the specs on the PC that you are training your AI on?
ОтветитьKart gpt
ОтветитьI’m surprised it didn’t master chain wheelies? Or is that a side effect of it not being able to input every frame?
ОтветитьEveryone enjoy his replies while it lasts, when he's bigger, he will never reply!🥰
ОтветитьThe AI on the last lap drove towards the finish line with an uneven angle. It would have reached its destination faster if it went straight ahead.
ОтветитьKeep this stuff going🙏
ОтветитьLETS GOOOOOOOOOOOOOOO IVE BEEN WAITING FOR THIS
ОтветитьGreat! Now teach it ultra shortcuts :D
ОтветитьPython moment 🤩
ОтветитьGonzalez Ruth Rodriguez Christopher Young Helen
ОтветитьAm I the only one who feels bad for the AI?
ОтветитьThis is all really cool, any chance you could help a brother out and show me resources to learn how to do this myself? Or perhaps a video tutorial on a smaller scale?
ОтветитьChatGPT Kart Wii
ОтветитьI hope wiimmfi won't have AI
Ответитьhey when can you test the ai in mario kart 7?
Ответитьthis is so cool i want to see more
Ответитьname the AI Funky AI
ОтветитьFind this so cool people like you exist
ОтветитьSolid video mate.
Ответитьyour videos are much work, thx for that tho!
ОтветитьAi does puyo puyo pls. The ones in game are not by neural network learning.
ОтветитьI believe it should be mathematically possible to calculate the minimum time between checkpoints. Then you can reward it more the closer it reaches this ideal
ОтветитьThe production quality of these new videos has been amazing
ОтветитьNo offense but i hate funky Kong he's probably the worst heavy weight in the game in my opinion
Ответить