![AI Tango](/img/default-banner.jpg)
- 35
- 2 346 160
AI Tango
United Kingdom
Приєднався 16 тра 2021
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.
AI Vs PRO Mario Kart Wii Player: Showdown with RedFalcon
#ai #mariokart #reinforcementlearning
An AI goes head to head against the UA-camr RedFalcon, using a variant of the Reinforcement Learning algorithm Rainbow DQN to learn how to play 4 different tracks.
0:00 The Challenge
1:20 Setting Things Up
2:30 What is the AI?
4:49 Training Starts
8:14 Final AI
9:47 Total Training Time
10:44 Human VS AI
12:51 RedFalcon Trailor
Check out RedFalcon's Video:
ua-cam.com/video/4-ff6na9cg4/v-deo.htmlsi=1QJgFOiuHIYTIoCe
Also thank you to my editor for editing this video!
@benji.botterill
www.benji-bott.com
An AI goes head to head against the UA-camr RedFalcon, using a variant of the Reinforcement Learning algorithm Rainbow DQN to learn how to play 4 different tracks.
0:00 The Challenge
1:20 Setting Things Up
2:30 What is the AI?
4:49 Training Starts
8:14 Final AI
9:47 Total Training Time
10:44 Human VS AI
12:51 RedFalcon Trailor
Check out RedFalcon's Video:
ua-cam.com/video/4-ff6na9cg4/v-deo.htmlsi=1QJgFOiuHIYTIoCe
Also thank you to my editor for editing this video!
@benji.botterill
www.benji-bott.com
Переглядів: 26 123
Відео
AI Learns to DESTROY Mortal Kombat (SUPERHUMAN PERFORMANCE)
Переглядів 7 тис.3 місяці тому
#ai #mortalkombat #reinforcementlearning AI uses a variant of the Reinforcement Learning algorithm Rainbow DQN to learn how to play endurance model in Mortal Kombat Armageddon. 0:00 Intro 0:57 How it works 5:59 Training Begins 10:22 Final AI Also thank you to my editor for editing this video! @benji.botterill www.benji-bott.com
AI DESTROYS The Centre Of The Universe | Super Mario Galaxy
Переглядів 20 тис.3 місяці тому
#ai #mario #reinforcementlearning AI uses a variant of the Reinforcement Learning algorithm Rainbow DQN to learn how to play the Final Level of Super Mario Galaxy. 0:00 Intro 4:05 Attempt 1 6:23 A bit further 8:54 Nearly there 10:45 Training 16:34 Final AI Also thank you to my editor for editing this video! @benji.botterill www.benji-bott.com
AI Learns Super Mario Galaxy
Переглядів 68 тис.5 місяців тому
#ai #mario #reinforcementlearning AI uses a variant of the Reinforcement Learning algorithm Rainbow DQN to learn how to play the Sweet Sweet Galaxy in Super Mario Galaxy. 0:00 Intro 1:39 Training Begins 3:58 24 Hours Training 5:39 Training Graph 6:36 GodMode AI Also thank you to my editor for editing this video! @benji.botterill www.benji-bott.com
AI Finishes Rainbow Road Faster Than EVER Before | Mario Kart Wii
Переглядів 37 тис.6 місяців тому
#ai #mariokart #reinforcementlearning AI uses a variant of the Reinforcement Learning algorithm Rainbow DQN to learn how to play Rainbow Road against Mario Kart Wii's own CPUs with items. 0:00 Intro 2:50 20 Hours 4:30 Running different AI 6:19 Final AI Also thank you to my editor for editing this video! @benji.botterill www.benji-bott.com
The Evolution Of My Mario Kart AI
Переглядів 49 тис.7 місяців тому
#ai #mariokart #reinforcementlearning This is the journey of how my AI has changed since I made my first video on Mario Kart Wii. 0:00 Intro 0:49 First Setup 4:32 First AI 5:37 Second Setup 8:20 Second AI 9:21 Final Setup 11:39 Final AI 13:56 This AI Also thank you to my editor for editing this video! @benji.botterill www.benji-bott.com
AI takes a ride on the BONECOASTER | New Super Mario Bros. Wii
Переглядів 8 тис.8 місяців тому
In this video, an AI uses Deep Reinforcement Learning to play level 8-7 of New Super Mario Bros. Wii. The AI was only given the screen to make its decisions, and had to learn through trial and error. Also the AI had no access to shaking if you were wondering why it never used the propeller. The specific algorithm being used was a slight variant of Rainbow DQN, a Reinforcement Learning algorithm...
AI Learns to drive a LAMBORGHINI - Need For Speed: Hot Pursuit
Переглядів 6 тис.8 місяців тому
#ai #mariokart #reinforcementlearning AI Learns to drive in Need For Speed: Hot Pursuit (Wii) When I first decided to do this I had no idea how different the Wii and Xbox versions of the game were! 0:00 Intro 2:13 First Attempts 4:47 Training Begins 7:29 Final AI If you're interested in how my AI interacts with the Wii emulator, it's done using the following Github - github.com/Felk/dolphin. Hu...
Can AI play a track it's never seen before? | Mario Kart Wii
Переглядів 169 тис.9 місяців тому
#ai #mariokart #reinforcementlearning AI uses a variant of the Reinforcement Learning algorithm Rainbow DQN to learn how to play 4 unique Mario Kart Wii tracks, then will attempt to use its knowledge to play 2 tracks it wasn't trained on. 0:00 Intro 3:21 Training 6:54 Final AI 7:58 Unseen Tracks Here's the modded version of Dolphin Emulator I use to make these videos. If you're a C developer, p...
CPUs troll AI with Items | Mario Kart Wii
Переглядів 163 тис.9 місяців тому
#ai #mariokart #reinforcementlearning By popular demand, here an AI will learn to play Mario Kart Wii with Items ENABLED! The AI in this video will be using a variant of the Deep Reinforcement Learning algorithm Rainbow DQN, to teach itself how to play the game with no prior knowledge, and no human input. 0:00 Intro 2:50 Training Starts 7:20 Final AI If you are a C developer please help on this...
AI Learns to DESTROY old CPUs | Mario Kart Wii
Переглядів 1,4 млн9 місяців тому
#ai #mariokart #reinforcementlearning AI uses a variant of the Reinforcement Learning algorithm Rainbow DQN to learn how to play SNES Ghost Valley 2 against Mario Kart Wii's own CPUs 0:00 Intro 2:46 Training 4:54 A bit better 7:58 Final AI If you are a C developer please help on this GitHub! Would allow me to get AI to play many other cool games. github.com/Felk/dolphin/issues/41 Also thank you...
Mario Bros is too easy for INSANE AI
Переглядів 125 тис.10 місяців тому
#ai #mariobros #reinforcementlearning AI uses a variant of the Reinforcement Learning algorithm Rainbow DQN to learn how to play a level of New Super Mario Bros within a day. 0:00 Intro 2:34 Coding 4:23 Training 9:10 Final AI Github I need help on: github.com/Felk/dolphin/issues/41 Also thank you to my editor for editing this video! www.benji-bott.com
AI Learns LASER HOCKEY
Переглядів 19 тис.10 місяців тому
This video uses modern AI to beat Wii Play's own AI from years ago. After explaining a little about how it all works, we slowly progress through the AI's training, watching it become stronger and stronger as it learns to play. 00:00 Explanation 02:18 Making It 04:23 Training Starts 08:50 Final AI Also thank you to my editor for editing this video! www.benji-bott.com
Neural Network learns to beat other AIs (Mario Kart Wii)
Переглядів 13 тис.Рік тому
Neural Network learns to beat other AIs (Mario Kart Wii)
AI Learns to DESTROY pensioner AIs (Mario Kart Wii)
Переглядів 66 тис.Рік тому
AI Learns to DESTROY pensioner AIs (Mario Kart Wii)
AI Learns to beat other AIs (Mario Kart Wii)
Переглядів 65 тис.Рік тому
AI Learns to beat other AIs (Mario Kart Wii)
Why are time and points not part of the rewards?
You have the best A.I. I have seen...All your videos are great well done!
I saw Redfalcon's video first then discovered this one
You should have your AI learn to play Rayman 1. . . The PS1 version. . . I'm sure it would rage quit.
I'd be curious to know the architecture of the model and the style of reinforcement learning. I'm assuming it's a convolutional dqn and if that's the case, I wonder how substantial of an improvement, if any, we would see if an ICM was used to both augment the reward structure and to encode relevant state information
9:08... YORT STORM!!!!
@AI Tango The vehicle’s AI should overlap either the Jet Bubble or the Spear.
One day we will we able to swap cpus with ais and the gaming world will be never the same. Imagine playing you favourite game against a learning ai that would be so fun
Request: let it train until it rarely crashes, then race against it.
Hm... Is it possible to teach an A.I. to make a bad option for a better pay off later?
I thought i'd let you know if you're making an ai that plays online, theres a decent if not very good chance it will be detected. I know what I'm describing is not your field, but there are controller mods for games like call of duty where it overrides player input to make better moves, and cheaters fly under the radar by lowering the settings as to not be obviously too good at the game. I wish you the best of luck, as its very unfortunate the bad eggs poison the water you want to work and play in.
I know you've made the ai play on multiple levels, but I'm curious if its more efficient to have a different ai trained for each level, and load one thats specific to that course, as opposed to have one ai model learn all the levels. I'm guessing the downsides is having to duplicate the model's file size for each case use on the hard drive.
25:50 - i can confirm. I found a lot of values in super mario kart, but the value for baloons in battle mode elude me. At best i can find the value for being hit.
I've been doing AI training for a PS3 game, so if you've got a PS3 game in mind I'd love to help you get started with that.
Metal Gear Rising: Revengeance
This is pretty cool. Which I could have been there for the stream. Would it be possible to guide the AI by playing in 4p mode?
you should release the ai to the public
I missed the stream by a couple hours rip
Train Ai until it can match time trials Wr. Than do 6 Ai vs the 6 best mario kart wii player
I bet if you let it run for a while it gets invincible
You’re very clever with the technology stuff. Well done
You should have cloned the ai and make it play on the other side as player 2 against it self to get even better 😂
Leave it on for a year
what resources would be good to learn how to do this myself?
is there any game like that u made, i really wanted to play those car games with those mechanics but i never found one!
Nah we're cooked
So you gave an ai dopamine receptors?
I'd love to see how much this AI could learn on it's own given a bit more time! Armagedon is a game with an incredibly high skill celing, and I'd love to see how long it takes for it to learn some basics like special moves and parries, all the way to things like infinites
Hopefully you'll answer even tho I'm a month late lol. But whats the reasoning behind not first teaching the AI how to complete the track through human playthrough, then apply the deep learning once it knows how to finish. I'm aware that this would involve mixing multiple AI algorithms, but I feel like it would be worth it. You wouldn't have to wait several days until the AI can finally learn how to complete the track itself. The AI could use that extra time learning how to get faster times
Let’s see human vs A.i
Is it possible to train the AI in a virtual remote gpu (such as colab) if you don’t have a machine with a gpu powerful enough?
AI from animal crossing 🤔
you should try to train the ai to beat real humans in an online race
for a future mario kart AI, you should have it play 8 delux. then, once its proficient against bots, put it onto the multiplayer scene! Also, just as an idea for the future, you should have the AI learn how to complete the tracks quickly from time trials where there are no other bots before dropping it into games with other AI's. Having an AI which can already drive around every track at blinding speed seems like a great place to start before putting them up against anything else
Pov the algorithm has chosen you today
I would love to see the source code for this project ❤
I still wanna see Marvel vs. Capcom 2. . .
Hey there, do you think it is possible to use a trained mario kart ai and let it use TAS inputs as a foundation, give it like 40 hours to improve that? I mean even if it is like only 50ms faster after that, it improved a TAS and that would be kinda revolutionary for speedruns
Song 7:20
That was very cool, I was just wondering if you could share the AI source code
Code: import dolphin_memory_engine as dme import time dme.hook() print(dme.is_hooked()) class Reward(): def __init__(self): self.last_comp = 0 self.check = 1.05 self.check_inc = 0.05 self.check_timer = time.time() def reward_function(self): reward = 0 terminal = False speed = dme.read.float(17964696) race_completion = dme.read_float(17964696) reward = speed / 2200 if speed < 37: return -1, True if self.last_comp != 0: reward += (race_completion - self.last_comp) * 100 self.last_comp = race_completion if race_completion > 3.99: return 10, True if speed > 100: reward += 0.1 if race_completion > self.check: reward += 1 / (time.time() - self.check_timer) self.check += self.check_inc self.check_timer = time.time() if terminal: ran = np.random.random() if ran < 0.25: #spawn location 1 elif ran < 0.2: #spawn location 2 elif ran < 0.75: #spawn location 3 else: #spawn location 4 return reward, terminal
Got you an discord server?
😮 Please tell me like do it i would try with other racing games
poor ai saw the lava tunnel and just thought "yeah, no"
This is an awesome series. Just found your channel and subscribed. Can’t wait to see what you have next! One idea I have to make the AI stronger, potentially by a significant margin, is to completely ditch Q-learning and instead switch to something similar to what DeepMind did 6-7 years ago with AlphaZero (or MuZero for a more recent iteration). Essentially keep training it in 2-player mode, and make it a champion/challenger model with the objective of the challenger beating the champion, and when it does consistently beat the champion, the challenger becomes the new champion. Rinse and repeat. I think one of the benefits to that architecture is that it forces the model to explore different ideas to try and beat the champion, and it’s much less likely to develop blind spots. There would be 2 major downsides with this though: (1) it would take significantly longer to train, and (2) the items boxes add a considerable amount of variability into the results, so you kind of have to run it 10-20 races (maybe more) for each training step to know if the changes made a difference. But I suspect it would figure out how to dodge blue shells, and potentially even figure out how to take expert shortcuts on certain tracks.
YOU HAVE INVENTED SKYNET.
Make all your Ai,s race each other in Mario kart
Ai tango hey you ever figure out how to play Mario kart 7 with ai I know the online servers are done but did you ever figure it out or you forgot about it? 😅
Should get it to use a different bike or kart. Possibly another character. And test it on other maps that have off-road sections.
Make them race each other
Soon...
3:50 That was a spin-drift - this is funny 🔥