Відео

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.

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

3:50 That was a spin-drift - this is funny 🔥