I create videos of AIs doing whatever crazy shenanigans I can dream up. It'll mostly go horrifically wrong and they'll find new wonderful ways of disappointing me, but occasionally impress me and persuade me not turn turn off their life support for another 5 minutes. I enjoy everything AI related, and long walks on AI generated beaches.
About bloopers, I HATE THEM like, idk how people can drive while not seeing 80% of the screen, I always end up in a wall or falling somewhere every times there is a blooper, so the ai struggling with it is normal as actual humans do too
This 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?
Another unbelievable feat Tango. You keep surprising me more and more with this AI, and scaring me too 😅🥲 but keep up the amazing work. I do hope we get some more videos from you soon! Also 2:24 the fade out was so quiet I only just heard the words mediocre player. Great job from the editor overall though @masqmp3
We 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😊
There’s a cool project doing something similar called kinoko which is looking to reverse engineer the physics engine. My ai uses images as input though, so sadly I still need to render the image
I hope it can learn any of these techniques by itself. For example, it learned how to rapid hop with no instruction. If the techniques save a lot of time though, I could look to give it some incentive
Very 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.. :)
the 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 🙏
Мне 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😂😂😂😂
Те кто не знает что такое сингулярность Это такая вещь то что у искусственного интеллекта есть сингулярность а это значит он будет обучаться до бесконечности то есть усовершенствовать себя Он играет в одну игру как например Mario Kart а потом он переходит на другую игру потом создаёт своё ии потом заканчиваются все игры переходят на приложение потом на телефон потом на роботов а потом захват мира их невозможно задержать даже если вы запихнули самую защищённую во Вселенной компьютером рано или поздно он просто Придумай как выбраться из компьютера
Amazing 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
I currently haven't made the repo public, however will do once I reach 100k subs. I'm currently trying to publish the algorithm I used for this video, and if it gets published I'll for sure do a video on it
Hello Mr. AI Tango! I enjoy watching your videos a lot and I would like to suggest something, in case you take ideas from your followers. I have two simple videos games that I would like you to build a reinforcement agent that excels at them. First, a Java game called Cannonball. There are two version Cannonball Confederation Championships wich 176*220 and 240*320 versions. And Cannonball with 176*220. For some reason, the 176*220 resolution version in both is way harder and the game is insanely hard to beat. (can be played via emulator(J2ME) for mobile and (KEmulator) for PC. If you train an AI to beat this game I would be impressed. Personally, the latter(Cannonball) took me 7 months to beat on mobile. And about a month on PC. If you can train an AI to beat this game I would be impressed. You can search the game on RU-vid to get a clear idea about what's it's about(it's a mix between ping pong and breakout), my personal favourite Jqva game of all time. Second, a Flash game called Dragon Fist 2.There are three sequels(Dragon Fist 1, Dragon Fist 2 and Dragon Fist 3) My personal favourite is the second since it's the most skill based. The game is a fighting game where you choose a name, pick your fighter, weapon, and fight to obtain a blade(The Dragon Master blade). Your goal is to build an AI that can beat the game and excel at it of course. You can search the game to know more about it, it's playable for me online through brave(don't know if it works still on other browsers since Flash was shut down). It can also be played via Flashpoint Infinity. This is all of course if you agree, have time and what I said is possible. Cheers!
lol 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
I understand the disadvantage, but it makes the training process massively faster. Also empirically allowing it to input every frame doesn’t improve it that much sadly
you 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
This is quite impressive, huge advancements were done. I suppose you could create agents for each track so the AI would depend on them whenever it plays, this would he useful when playing against other players / cpus?
Hey NMeade, I’m a huge fan of your channel! Would love to work with you if ever you’re looking for a new video idea, including trying some other tracks
