Can AI play a track it's never seen before? | Mario Kart Wii

[@sammyclassicstarfoxfan9827]

I think putting the AI on a track it already learned, but with a texture hack could be interesting, or putting the AI on a different track but with the same textures.

[@aitango]

That would be a cool thing to see, you'd expect it to be able to adapt much faster

[@ThePapaja1996]

Or drive it backwards

[@nashh600]

​@@aitangoor a different vehicle

[@phabrick8r21]

Bikes vs Karts @@nashh600?

[@tribble_omg]

The track in mirror mode

[@DoMorrMusic]

Now I want to see how well the AI does on every track, and then have it go against a human.

[@vincenzofranchelli2201]

Human would still crush it

[@captainphoton1693]

​@@vincenzofranchelli2201hen his little brother

[@zxqu2622]

@@vincenzofranchelli2201 give the ai 10000 hours of non stop training and then do it

[@vincenzofranchelli2201]

@@zxqu2622 i wouldnt be surprised. U got 10000 hours?

[@zxqu2622]

@@vincenzofranchelli2201 no i don’t even have 100, but although i would love to see it happen against someone with that many hours

[@ghastlyGrenadine]

I think I get why the AI struggles so hard the moment it makes a single mistake outside of training mode... If it doesn't fall off a cliff, it has no idea how to recover! I think if you could figure out how to train this AI to recover from mistakes? It would be a top player.

[@glitchy9613]

I think just add a reverse option

[@RushyoTakha]

@@glitchy9613 same issue. it'd never choose to use the reverse option after a while because it would never need to use it, so it wouldn't realise when to put it in to effect.

[@budgetcoinhunter]

@@RushyoTakha I'm not sure. I'd think that it would quickly learn that if the rewards start to decrease rapidly, it should probably try reversing and then going towards the next checkpoint.

[@ghastlyGrenadine]

@@budgetcoinhunter the problem is that he has it set to auto kill it after a crash... he'd need to train it specifically to recover from a crash in a specific training ruleset

[@ghastlyGrenadine]

@@MustacheMerlin my idea was more of to pre-pick a few definite crashes around the course and give it a huge reward for raising it's checkpoint flag by a decent amount, but I suppose that's also a good way to train it for crashes and normal play all at once...

[@ChuckSploder]

There's so much stock footage in the intro I thought it was sarcasm

[@OfficialBiggBenn]

I really like that you keep pointing out the problems with AI approaches (not conceptually, I mean practical problems, like how you need a convolution, and how improvement quickly stagnates). Too many people out there who only point to the cool things possible with technologies from the AI field and extrapolate from there.

[@jonahschreiner6531]

video idea: ai plays against itself (as other racers) and can use items. reward is based off its distance ahead of the others (i.e winning the race)

[@alvaro97vlc]

Amazing idea! It could take so much time, but seeing creative ideas like being last in the last lap to get the bullet and crush the game or the IA learning how to aim to other player with a shell... Truly interesting and at the same time scary

[@sushi_rolld]

bump

[@fernbear3950]

ML engineer/researcher here. Good stuff. Try training but with occasional input perturbations based upon the average score achieved by the network (will self-normalize as it continues to get better). This should make it more robust towards running into walls, etc, trying to approach a learned invariance. You'll likely need a power distribution of multi-button inputs to simulate things that would cause you to thonk into the wall like hop cancels and etc. This will also provide the requisite noise for your network to explore new strategies, ala genetic evolution. Hope this helps, and this should greatly ameliorate and/or fix your issues here in terms of/w.r.t. the retraining, esp as the 'learning space' of the network becomes so much larger. Gating it based on performance as well ensures that the regularization/extra data-learning/learning to be robust happens naturally as a curriculum, and affords a consistent level of information ingest to the network over the course of training.

[@connorkapooh2002]

have you ever read his code or listen to his explanations of convolutional layers

[@fernbear3950]

@@connorkapooh2002 ?

[@trunkit8749]

I’d love to see this ai race on a track where every texture is replaced with a color for its corresponding material (like off-road, road, wall)

[@gavin_bigred]

It would be cool to train it on every map, and then give it custom maps and see what it can do with that knowledge. If it’s possible maybe even other Mario kart games

[@UhDots]

I’d love to see the AI learn some custom tracks from CTGP as well as any AI’s you’ve had to kill because of failure. Great video as always though!

[@mjcox242]

CTGP (Wii) isn't possible with this (easily) You would need a tas bot hooked to a real Wii, then deal with the added anolouge noise and in-ability to save state.

[@theunpopularcuber9554]

​@@mjcox242The custom tracks (as far as I know) should still be possible though.

[@nixienooo]

I’d love to see an AI attempt mushroom peaks

[@mystora7159]

​@@mjcox242you don't need ctgp to play custom tracks

[@mystora7159]

I think it'd be more interesting to see other tracks not in ctgp, specifically the crazy ones like nightmare, electric shredder (lol) and anti gravity area (i think that's what it's called)

[@y..l..8412]

I think you could get better consistency if you added some random filter to the different images. Making it less relying on the specific looks of levels

[@sjoerdgeraeds6757]

Noise filters

[@OuroBoros_Games]

But this does make it lose potential?

[@TVPInterpolation]

​@@OuroBoros_Gamesusually it isnt the case, computer vision can adapt in such ways rather gracefully.

[@user-qw1rx1dq6n]

@@OuroBoros_Gamesweirdly enough usually it’s quite the opposite neural networks tend to have too much capacity that starts causing something called over fitting where the network just becomes really good at memorizing the data you’ve shown it that hurts generalization but if you add noise to the input the network can’t memorize all the data and has to rely on heuristics more becoming more resilient

[@thejunkman]

I think that is the main thing that is the problem with any of these simple AI's. They don't know and never will know they are playing a game, much less Mario Kart.

[@nicolasn12]

"its going to just rely on the screen" finaly someone did what i always wanted.

[@aitango]

I really like that it only uses the screen, makes it feel like it has a level playing field

[@hansjmo]

when approaching a limit like a lap time, progress in terms of time will go down, but the skill is improving. I would not say that Twice as fast is Twice as good, it's way more than that :) if someone is 1% faster than the other close to the theoretical limit, I would say that he is way more than twice as good because it gets harder and harder approaching the theoretical limit :)

[@joep2999]

That's a great point. Maybe the fitness function could be influenced by the difference between the final time and the human world record. I think an exponential of some kind would capture the skill difference you're talking about.

[@looki4561]

Loved the commentary on this one! Defintiely feels like an improvement to the last video. Overall the video felt made a bit better, but I can not put my finger on what it was.

[@aitango]

Really glad you liked it! I'm trying my best to improve each video as much as I can

[@g_fenocchi]

It would be cool to compare how the AI's average reward compares to that of a human.

[@luis-sophus-8227]

well, humans mostly struggle because of their general skill, which doesn't apply to ais ais are perfect skill but no perception we are perfect perception but no skill

[@bananajamin8284]

Nah he’s saying if a human driver drove how much reward would the AI detect

[@Wato-1876]

i heard jort storm in the background lmao, also amazing video

[@kalebheavyshadow5838]

Is it only me but the first 55 seconds kinda went crazy

[@badischertraum1806]

My dream would be a 1v1 between AIs to see how different or similar they learn and if one of them winning the most races

[@Atlas_Redux]

Could be interesting indeed, having parallel competitive model training.

[@samuelthecamel]

Now for the ultimate challenge: AI vs. Rainbow Road

[@NeXaSLvL]

its almost like it has an infancy stage for the first day

[@AntoLne]

Your videos are genuinely such good quality and keep getting better! I really enjoy watching them and I'm sure you'll soon get the recognition you deserve!

[@Delkaryon]

I wish you the same chose

[@NZIA]

will an ai be playing in esi4

[@aetherspill]

Hi! I love your videos and they're super interesting to me as I go through my software engineering degree. I'd just like to say something about a thing you said in your video. 5:27 "Here's where our AI brings an objective perspective to the table. It doesn't possess these personal biases or preference; it simply just learns and adapts." I think it's important to make sure viewers know that reinforcement learning models are not necessarily always free of bias. It's definitely true for this example and your other Mario Kart AI videos as there's a definitive metric for measuring success in a goal's completion, but reinforcement learning is not a perfect solution to erasing biases from a problem. Whatever biases the creator imparts into the AI (i.e. what is considered rewardable/punishable behaviour), unknowingly or otherwise, will influence how the AI makes its decisions. It's up to us to determine these biases and be aware that we have the ability to make them intrinsic to the AI. Obviously you never claimed that reinforcement learning is free of bias, so I'm not trying to make a callout. I just think this is info that more people should be aware of :>

[@l-bear_0528]

I’d be interested to see a pro MKWii player go against this bot! Keep working hard!

[@dougfoster445]

Thanks for putting the music u use in ur summary and notes! Love the tracks and was grateful you gave the artist credit!

[@starwars4427]

My biggest wish is to see how it fares vs a human player after like the 120 hour mark. Cause just the limitations you put on it with the controls would probably make it pretty easy to beat

[@chicklucas6682]

150 hour AI vs 10,000 hour player, battle of the ages

[@starwars4427]

@@chicklucas6682 Let it run for a while then! I just think itd be interesting to see cause we always talk about how good and objective the AI are so seeing how it fares vs a human would be cool.

[@potatojuiceultra]

@@theAstarrr It looks like it would actually be pretty easy to beat, since it doesn't go for as many mini turbos and does a lot of random unnecessary hops.

[@zchilly7775]

@@theAstarrr I'm not a grandmaster at Mario Kart Wii, but even my slightly decent lines could stomp the AI. They aren't chaining mini-turbos into wheelies, and they constantly lose their wheelie speed by hopping. I would be 11% faster and gain time on every straightaway, making it a wash

[@icanlevitateoff]

these videos are super interesting, kinda nuts that after you trained the initial 4 tracks an hour of training was enough for more tracks

[@aitango]

Yeah I honestly didn't expect it to adapt quite that fast

[@Bleuthatup]

Ah, yes, the type of literal video editing where if the voice says “square root”, the video shows a square shape, and, next, the root of a tree. Premium stuff

[@8BitRip]

Just show us what your doing, not random stock footage. It’s so distracting from the actually interesting content

[@duckdudette]

"Less savvy side-kick" *shows picture of a robin*. I see you, editor! 😂

[@leafly7917]

I'm like 90% sure it's an AI that edits those gifs lol

[@phabrick8r21]

@@leafly7917 Who's editing the film, Batman?

[@leafly7917]

@@phabrick8r21 bro what

[@PinkyNardo]

Again another amazing video on how AI can adapt and learn then carry its previous learned attributes to the table in the next stages. It is an awesome way of showing how it can retain its reputation and keep up. All it has to do is tweak a little for the next track and its all good, and all of that is part of the previous tracks processes. This is the AI I want to see impact the future of gaming. Let us Pray 🙏

[@illford]

Ngl tho if people took this shit online I'd be pissed

[@apr1l-813]

no fucking way bro is using JORT STORM for the bgm

[@theftking]

After training it for a short time on the new courses, is there a possibility that the AI would actually perform _worse_ on the initial courses it had spent most of its time training on? Basically like, could the AI have become more intelligent overall for a diverse set of courses, yet less specialized for the initial four it had been tailored made for?

[@austinhurst467]

I hope winter comes soon for you to keep your room cool. These videos are awesome!!!

[@aitango]

Thank you, I've never been so excited for it to get cold haha

[@WhyHelloThere779]

I know this would probably take way longer, but I’d love to see the ai with all normal controller inputs (minus 360* turning) and only being rewarded based on what place in the race it came. Wondering what weird strategies is would come up with to win, maybe find shortcuts.

[@alansmithee419]

It would never learn to complete a race. You would have to take a trained AI, and then switch to this reward structure. If you never reward it unless it finishes a race it will never discover that it needs to finish the race in order to get a reward.

[@RikkunFops]

If we were to read memory well enough, we could be able to learn when the player character is offroad and punish the AI simply for going offroad. This may speed up and teach the AI to better map out the safe areas of the circuit.

[@Ascension721]

I get the tiktok text intros are good for the algorithm and thats good and all, but seeing the text come up word by word with the text at the bottom too is kinda funny to me

[@jackatk]

0:28 What am I even looking at

[@blockmath_2048]

Finally! An AI video where the AI actually learns to drive, and not spit out an evolved series of inputs!

[@mrbanana7110]

Now i have my answer ty Next the ultimate test would be to learn the item again and then all of the tracks just so it know the color and then make it compete against mariokart pro but ik this could be impossible as how difficult it looks like

[@eduardozanotti7046]

Awesome video bro!! Great AI you created there. Would love to see more

[@branbri8178]

I wasnt a big fan of the random images and gifs but the racing visuals were entertaining :)

[@devilblackdeath]

I'd love to see every track added in little by little ! See how much that reduces the training time every time, maybe even to the point that it would actually be able to complete a race on its first try ?

[@professordragon]

Really impressive that it was able to adapt to the new tracks so quickly!

[@bricksalad_]

I would really like to see a video of how an AI (similar to the one in your training with items video) could handle HARD CPUs, unless it is already doing that (which would be amazing!).

[@aitango]

It's currently not against hard AI, but that would be really cool and something I'll look to do in the future!

[@jolkyb2039]

Okay, video was fantastic. Great job. But I have to know... Are you using AI to choose the b roll footage? It's like... Related to what you're saying but only by a thread.

[@dinamiteurdinamiteur2324]

Now, take this AI trained on 4 courses and put it on 4 other ones and see how it adapt. Do it 3 or 4 times and you should have an AI who can plan every tracks or almost

[@rafaelleone678]

5:39 I laughed because he was doing so good and the speech sounded so motivating

[@Woopah194]

This video gave me a interesting idea what if you trained a ai on a track but then once it learnt the track you put it in mirror mode

[@Luweg01]

Really cool to not only see that the ai is doing decent on the unknown tracks but also manages those after very little training. Why dont you do this more often and always start from ground zero ? I would love to see you give an ai a really good control over the game, then start with one track until it can beat it consistently and then go to the next track. It would be interesting to see how long it takes for each new track and how its driving on an unseen track might change depending on the tracks it has seen. You could then see how it performs on the original stage after it has seen so many others. You could then make changes again like enabling npcs or items to see who that changes it or how long it needs to adapt. The important parts are to show enough footage of the new stages and performance that we can see the improvement. You could also turn it into a series, a challenge of sorts to master the entire game.

[@autumn4442]

I think the purpose of starting fresh each time is because they're trying to test something new. If you start fresh, you can see how the change affects how the A.I learns differently and compare it to a control. It's really about what your goal is: to see how they learn, or how they adapt when thrown into a new set of circumstances.

[@Kaitri]

i like how the thumbnail is basically "ai never seen before" sounding like this is some crazy god ai :D

[@Strobenz]

This is amazing. Would love to see this AI attempt one of my tracks!

[@Joe_789]

Bro really spent 3 minutes on a single intro 💀

[@Vernafveik]

I love how the footage used to represent the AI being taken is someone robbing a car

[@jahlove40]

Without a doubt: best videos ever, cheesiest b-rolls ever.

[@aitango]

I'll take that as a complement haha

[@durpy4442]

been waiting for this stuff thanks, instead of just training one for each map

[@realElo.2]

sorry if this isnt true, but i mean this in the kindest way possible: why does the script feel ai written?

[@Colewis1]

lol

[@RM-mv5yz]

Would love to see the AI go up against a human.

[@GroveOfGraves]

Have you considered livestreaming the training process of one of these to KZbin? That way you get to record all of it not on your device, plus people can watch if they wanna and check in on its progress. The only downsides I see is if you're data capped or bandwitdth limited

[@aitango]

I actually did livestream one of my previous AIs! I might do it again, but the stream is pretty boring since the improvements are so slow. Also I wouldn't want to livestream it unless I know it'll work, which isn't usually the case

[@shal6178]

It really makes sense the AI progress slows down after reaching a certain point, cause like in any speedrun there is less ways of saving time so you get just some micro optimizations of the run

[@Mezuzah87]

What happens when you put the AI back on the original tracks? Does the new track's learning hinder it? Does generalizing it to additional tracks lost its specialization to the original? Maybe this is a silly question lol.

[@birdieboy02]

i think that's called 'catastrophic forgetting' and it's definitely a legit concern

[@JordianLoL]

I assumed he trained it on all previous tracks as well just added the tracks into the pool. Or maybe he has weights so he weighs the new maps really high, but the ai still gets some old maps so it doesn't completely forget.

[@That_Awesome_Guy1]

@@birdieboy02 I don't know much about this stuff, but what if as they did the transfer learning back and forth on new and old tracks they slowly increased the size of the network? I think that would help it generalize while still allowing capacity for remembering things it has learned.

[@DougSalad]

Stil camt seem to stop them bots from hopping around like bunnies, but was REALLY cool to see how relatively quickly it could adapt to the new courses

[@DeloofTegOrb]

I love all the stock footage used in this video for absolutely no reason lol

[@aitango]

Glad you appreciate it haha

[@DeejayNiXoT]

Would AI ever stop driving Zick Zack?

[@Den-gw3hs]

Heres an Idea: can AI beat champions road. (i think this would be near impossible maybe do this in the future)

[@fattyMcGee97]

I look forward to racing games in the future using this sort of tech, as well as basically every other game type. It’s going to be a lot more engaging fighting an AI that actually knows how to play the game as opposed to the more simple AI’s that we currently see. Especially if the neural network ones learn as you play.

[@illford]

Tbf idk how good it can be at Mario Kart considering it doesn't really seem to play with Items or any kind of semi-advanced maneuvers. Item wildly scale how good a player is. I also just really wanna see it aim green shells

[@fattyMcGee97]

Tango already did a video on this and showed it could be done. His AI wasn’t perfect, but hardware and time limitations is what prevents home from being able to push AI farther. Now, if you hand this to a team of devs with access to much better hardware, I am sure we’ll better results. Also Tango’s results were very promising with his limitations so I’m still looking forward to seeing where neural networks can take us with regards to gaming.

[@Mobtrapper-hq8is]

Now try changing from Funky Flame to a Kart after it’s mastered an entire GP

[@austino545]

7:10 JORT STORM

[@llamacrafting9738]

Have you thought about putting together a tutorial (video or text) about how to setup the felk/dolphin repository you are using? I was trying to get it running but its setup documentation was not that great.

[@sincerelytheo]

This is fascinating. I noticed you chose tracks that were relatively free of hazards, cliffs, jumps, etc., which makes sense, but it makes me wonder if it would be possible to ever train an AI to handle all the craziness some other tracks would throw at it

[@Atlas_Redux]

It depends what resolution they're running the CNN AI at. We usually downscale images down to as small as 64X64, making most objects near impossible for it to even see. Higher, the better, but takes enormous amount of hardware.

[@EbonyWolf.]

Sup @aitango love your content. A lot of people doing neural networks on youtube seem to overlook something. In your input layer. For whatever inputs your using. Its often better to use the variance of the value as the input (or sometimes both). So instead of say, reading RGB absolute value of a pixel, it would see the change of the value. Absolute values are often too arbitrary in nature which can make learning them take longer.

[@misterperson3469]

This was great, exactly what the previous videos made me curious about! Though a note on the "objective difficulty" of tracks: wouldnt a reinforcement learning AI be equally susceptible to gaining a bias due to the track misaligning with how its learned to drive up to that point as a human? Not to mention issues with the reward function, say it can drive off road losing all its speed but hitting the next checkpoint faster. It needs to drive well through that part of the track for it to stop running off the road for that sweet reward bump.

[@chadd990]

great, now you can train it to navigate the main menu, start up a new game, and complete the Lighting Cup

[@AetherBirb]

I love these vids mate. Your explanations are good n all! Keep it up!

[@hellium6613]

You should try making a similar ai for a game called track mania, the scenery is so much less diverse and the driving mechanics are simple but elegant. I also feel like only allowing the ai to see the screen isn’t doing us humans justice, we memorize tracks, we don’t just look at the screen and decide what to do based on that. Either way, great video 👍

[@insertnamehere9242]

Pretty sure if you switched left from right on my control stick it would take me more than a couple hours to figure it out and fully compensate

[@aitango]

I reckon you'd pick it up pretty quick, but I can't say I've tried haha

[@muffinking2938]

I heard jort storm around 7 minutes I know the original isnt jort storm, but the two are lunked im my severely broken mind

[@mackowacko5166]

It’d be cool if you let the ai train on one track only for a whole year straight, and then have it go against a human on that track.

[@tristanderoo]

That Yoshi Falls race was impressive!

[@dmace14]

I just noticed the background music in some of the video is the same stock music Charlie slimecicle used to make jortstorm and I’m now hearing it everywhere lol

[@memcgee7832]

this is what we've been waiting for

[@CoreyDavid22]

Nice Vid man!

[@bugsisland3061]

The final evolution of this AI is playing other kart racers

[@JRS06]

So this is why there's just a million people who always play as Funky Kong and all play fiercely competitive...

[@Person-who-exists]

Would be funny if you gave it access to the whole controller

[@cliftonchurch6039]

Out of curiosity, have you tried running an AI with any amount of training on a track that has a section where you are controlled across a large jump? It'd be interesting to see if from hour 0 it ever realizes you don't need to do anything during those moments, and how long it would take a trained AI to retrain for this vastly different track element. Even wilder, can you take this AI and use it on another mariokart game, such as MarioKart 64? How much training (per game) would be needed to make a generalized MarioKart AI, with the four outputs you set up initially?

[@FormulaHavocOrland]

I think this is the best way to train ai because its not just memorizing the track. Plus it gets a chance to prove what it’s truly capable of, rather than just continuing to race the same track. Because how do we know whether or not its memorising.

[@someperson8249]

I like all the stock images that have minimal relation to the words said

[@Delkaryon]

Nice video ! I have a idea to make it learn faster : using its current position in the reward. I think at the beginning it makes zigzags to gain speed, but it is wasted in zigzags. Giving the position will ensure the speed gain is efficiently used

[@BobzBlue]

Now put one on ctgp (Maniacal laugh)

[@aitango]

(AI cries in mushroom peaks)

[@phabrick8r21]

@@aitango *Clip montage intensifies*

[@kingjuliangaming15]

Yo is that Funky Kong, the character from Mario Kart 8 Deluxe?

[@RyluRocky]

Great video! However I think you need to turn down the editing algorithm down just a tad, in terms of the frequency of cuts and images/videos it shows. I’m assuming your using a program that reads your script for some keywords then searches it on Google and uses Stock photos/videos it finds on the internet or from a local storage bin of media you own.

[@donskelz7771]

Just curious but does every video use the same code or is it revitalized each time?

[@FranXiT]

This is your best work yet! The improvement since your previous videos is incredible. Keep it up man!

[@gamingstation0608]

Unrelated but this makes me want to go further with some CPU edits I made once. You make me want to release a pack would include upgraded CPU action codes in the KMP files of courses, CPU max speed edits, and if I manage to do it, improve CPU's overall item use params.

[@zephielexe4527]

Man, do I wish I knew how to do this. I would love to take an AI and train it to play fighting games. And I’m also curious what the best time your AI gets on those tracks are.

[@EXFrost]

Fighting games would be hard i think

[@phabrick8r21]

Smash Ultimate Amiibo without an Amiibo? Nintendo would be furious 😅

[@EXFrost]

@@phabrick8r21 comment has nothing to do with amiibos. Why smash ultimate amiibos??? You know they were in wii u too, why specify? Also AI is way way more advanced than than the amiibo "learning" system nintendo has in place in smash. Itd be easier to make an ai for traditional fighting games rather than platform fighters as you dont have to worry so much about movement and stage stuff which would be the most difficult thing id think. Itd be very cool to see either tho tbh. Someone might have already trained an AI in melee tho iirc. Haha you read this far and didnt realise im being an asshole and overanalaysing your comment on purpose hahahha

[@SuperAronGamerMNO]

Amazing! I would like to see what happens if you train it on even more tracks and see if it becomes better at driving on new tracks. Also, I have an idea that might be a bit far-fetched for this type of AI. Could you increase the randomness of the AI and try to make it learn either a built-in shortcut or even a glitch (if those are common in MK Wii; I don't know much about this specific game)?

[@CodeF53]

I feel like a better analogy for the retraining is playing on mirrored tracks.

[@natsoph1924]

Loving these AI mkwii videos, you should outsource your compute to your subscribers to make something extremely strong!

[@natsoph1924]

Also would be interesting to see it using karts

[@hephaestus8266]

Jortstorm, Jortstorm’s coming tonight.

[@arikgorun6004]

It's very interesting to see what is essentially known as few-shot learning in other areas of AI, done with reinforcement learning. Curious to see more of that. I am wondering if there are any research papers exploring this

[@aitango]

Yeah its a pretty interesting problem. I've read the odd paper or two on the subject, but there aren't masses of research on the topic. I this video was a slightly easier version of few-shot learning since the new task was so similar to the old one

[@frex102]

instead of learning tracks i wonder how good he could be on the other gamemode A.I is something completely new to me (in a sense that im actually curious about their potential) i’ve been gaming the past 15+ years of my life and being myself not much of a pvp player i often find A.I in different game intricate I know they aren’t neural network they work based on pre determined pattern and I often wonder how far can neural networks go if we give him a ridiculous amount of hour would he be the best at what he do ? would it be better than human ? this is kind of my dream A.I tbh normal A.I can already do crazy things human will never do but even with that they aren’t better. there is a game called rain world i would love train the A.I to (plus screen wise the A.I won’t have much trouble at all recognising things) but I am unable to get a PC myself and I will patiently wait until I get one.

[@illford]

In this instance with the current conditions it probably wouldn't be better than a human, which is only because the AI doesn't use items, items are like half the life of this game in FFA so not using them puts you at a big disadvantage, the other issue is you need to give it a lot more control but that just increases the amount of time required to an unviable point for any normal person tbh