This AI Learned Boxing…With Serious Knockout Power! 🥊

❤️ Check out Perceptilabs and sign up for a free demo here: www.perceptilabs.com/papers
❤️ Watch these videos in early access on our Patreon page or join us here on KZbin:
- / twominutepapers
- / @twominutepapers
📝 The paper "Control Strategies for Physically Simulated Characters Performing Two-player Competitive Sports" is available here:
research. publications/...
🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Aleksandr Mashrabov, Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bryan Learn, Christian Ahlin, Eric Haddad, Eric Martel, Gordon Child, Ivo Galic, Jace O'Brien, Javier Bustamante, John Le, Jonas, Kenneth Davis, Klaus Busse, Lorin Atzberger, Lukas Biewald, Matthew Allen Fisher, Mark Oates, Michael Albrecht, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Ramsey Elbasheer, Steef, Taras Bobrovytsky, Thomas Krcmar, Timothy Sum Hon Mun, Torsten Reil, Tybie Fitzhugh, Ueli Gallizzi.
If you wish to appear here or pick up other perks, click here: / twominutepapers
Thumbnail background design: Felícia Zsolnai-Fehér - felicia.hu
00:00 Intro - You shall not pass!
00:49 Does nothing - still wins!
01:30 Boxing - but not so well
02:13 Learning is happening
02:39 After 250 million training steps
03:10 Drunkards no more!
03:29 Serious knockout power!
04:00 It works for fencing too
04:20 First Law of Papers
04:43 An important lesson
Károly Zsolnai-Fehér's links:
Instagram: / twominutepapers
Twitter: / twominutepapers
Web: cg.tuwien.ac.at/~zsolnai/

[@wongwu]

"I fear not the AI that has trained in 10 billion simulations once. But I fear the AI that has trained in one simulation 10 billion times." - Bruce Lee probably

[@warrenarnold]

No bro, this was Sun Tzu. Page 205 guyz believe me

[@zombiekiller7101]

Ai trained in 10 billion simulation will kill the other Ai in all the simulations except that unique simulation in which he was trained 10 billion times -Zombie killer 2021

[@Korea-Lens]

@@warrenarnold why denigrate yourself and a good joke with a terrible joke like that bro

[@piccalillipit9211]

VERY GOOD

[@anonymousshawn9996]

Nah, it wasn’t Bruce Lee who said that, it was Luce Bree.

[@qhc157]

"Everyone has an algorithm 'till they get punched in the mouth." - AI Tyson

[@antwartalley3327]

underrated comment

[@user-in4dv2bm6v]

here at 7 likes remember me when you get a thousand! :)

[@NhanChanh]

AI Tyson, i knew him since the gpt lab

[@azoicxx]

AHAHAHAHAHAHHA

[@mak00ileven]

This comment made me cry... lool so damn funny good shit

[@splintedvibesvibes1591]

"After 130 million steps of training, it can not even hold it together" My life

[@alaouiamine3835]

Lmao

[@chevvvv]

😔

[@VishnuPandey93]

rip

[@samsebin7895]

:'(

[@atomictraveller]

"look what it does at *420* million" aww it tries to take a hit

[@rian8024]

The funny thing is that due to their bodies having the same measures, they've learned that cross countering was the best strategy. It would be interesting to see the same experiment, but with different measured characters.

[@pierrelebonet6053]

Yes I guess small differences in mass would create a much more divers game.

[@abdelhakyac7285]

where are those cross countering, i see none

[@jimmythe-gent]

Yes, exactly. Also, they're point fighting. Not trying to win by disabling the opponent. Id like to see this again with better AI boxers, and each have a health bar. Max damage for certain headshots, certain bodyshots (liver, solar plexus maybe). And then see what they come up with. Will they take little jabs to the face to land a huge cross to the chin? That would be amazing to see the techniques after thousands of simulations

[@raylopez99]

@@jimmythe-gent Rope-A-Dope?! BTW using an AI-engine they came up with a chess engine (AlphaZero) that beat all other more-algorithmic engines and 'solved' the game of GO, and poker, that previously were thought to be immune. Progress for the machines, bring 'em on!

[@jimmythe-gent]

@@raylopez99 yeah the ai machine beat that other chess ai- i think it was called "fish ...xxx..something"

[@Teth47]

An important thing to remember with these learning algorithms is that they're going from "less skilled than an infant" to "basic boxing" in *a week*. It sounds like a long time because we're used to computers operating in milliseconds, but imagine going from not realizing you have limbs to walking around and throwing punches in 7 days. That's a huge amount of learning, even in this simplified system.

[@DontfallasleeZZZZ]

It's a week of computing time, it's not a week inside the simulation. The simulation goes on for a billion steps at 30 Hz, so about 30 million seconds or about a year around the clock, or 4 hours of playtime every day for 6 years, which is interesting because it's in the same ballpark as the time humans require.

[@gwills9337]

@@DontfallasleeZZZZ great points, I was wondering about that!!

[@SSingh-nr8qz]

@@DontfallasleeZZZZ Time is relative based on perspective and scale of where it's measured. A great example is Geological time, vs the span of human existence. Then you go out to space and have all kinds of weird time effects like time dilation. In this case we have "computer" time.

[@nothingTVatYT]

Furthermore even if we talk about a "big" neural network it's nothing compared to a human brain. Also the sensors i.e. the input variables are hardly comparable to what we can use and train on which of course goes hand in hands with the many sensory values to process. In the early days someone working with AI claimed we try to make a creature with insect-like neuron knots behave intelligently. Considering that it's amazing what can be done.

[@haraldtopfer5732]

But why do they always start from scratch. Couldn't they utilized pretrained networks or classic algorithms for a starter and build on that?

[@technorazor976]

0:50 I mean, I would also stop playing if my friend suddenly had a seizure.

[@BVW16]

Blue: And then he turned himself into a ball. The funniest shit I've ever seen.

[@shadowling77777]

@@BVW16 Kek

[@py-3366]

This comment made my day. Thank you sir.

[@thomasseillers3905]

lmao, made my day XD

[@corneliusjohnson5963]

I think he "juked" the other player

[@samc2950]

I’d love to see a boxing simulation where one character has a shorter build or shorter wingspan and see how it adapts to its disadvantage

[@crystalores4386]

that would be cool

[@boyarvalishin9565]

HEAD MOVEMENT BABY BOB AND WEAVE

[@beansoclock8748]

@@boyarvalishin9565 LET EM HAVE IT MAC BABY

[@revimfadli4666]

I'd love to see boxing with wings

[@agr0nianTV]

Yeah that'd be really cool

[@Soulsphere001]

I think the reason the blue AI kept losing when the red AI fell over is due to over training for one possible outcome. The blue AI expected an attack and only knew how to win when it was being attacked but didn't know how to proceed when not attacked. It overcompensates for the expected attack and then falls over.

[@stroggosaw299]

same thought

[@comradpingu5745]

So by training AI to do things for rewards, it created AI capable of being ass-holes? Interesting... Just like real life humans (most of the time)

[@conemerchant]

a true counterpunching merchant

[@TheKRID54]

Basically it hasn’t been studying the game itself, but another AI’s analysis.

[@Soulsphere001]

@@comradpingu5745 I'm guessing you're joking, but the serious answer is no. The A.I. just does what is going to win it the match in the best (probably fastest) possible way. Though its reactions all depend on what values it gets for inputs.

[@astryl-01]

we should try to make a simulation where movement costs them energy to see if they would avoid too many small and fast movements

[@SSingh-nr8qz]

This is a very good comment. In the real world people don't have unlimited energy reserves. That's why most average people can barely fight for 3 minutes on average before gassing out. Since muscles require energy and different actions use different amounts of energy, your idea makes a lot of sense for realism. In the real world, if you had unlimited energy, you would act completely different.

[@tesfatesfaye6262]

Very true

[@lazarus8453]

probably it will make computing 1 year

[@larion2336]

Agreed. In addition to that the reward mechanism needs to be more complex than "I touched the enemy and didn't get touched." I note the bots are just tapping each other for the most part, though there was that one decent knock. But things like momentum should ramp up the reward considerably so that a proper full contact punch is preferenced over light jabs (although this is actually not the case for fencing).

[@sumbody694]

It should also have some kind of way to alternate punches occasionally because something that was obvious is that the computer is always going to go for the most "advantageous" move it can seeing as it swung with the leading hand 100% of the time showing it has no interest or understanding of diversionary tactics and advanced problem solving.

[@dionyzus2909]

"this ai showcases agents that can learn boxing" red guy falls for no reason whatsoever "wait a minute -- that's the soccer ai, sorry"

[@yaboi1288]

lol so true

[@denispeda]

@@yaboi1288 neymar AI

[@GigaChadL337]

*football

[@Star-Gazor]

@@GigaChadL337 European lies

[@quill7889]

@@GigaChadL337 It can be either holy fuck, depends on where you're from

[@k-fedd]

Once the AI get so advanced you should save copies of individual behavioural patterns, name them, and start an arena. Maybe live stream fights? Would this not be awesome?

[@awebo2292]

Yeah men that's incredible idea

[@jamescarbon3853]

I think they're going to load up simulations of prime Ali vs Tyson. Then go to other sports like prime Michael Jordan vs Kobe Bryant or Lebron to see who is the goat.

[@builderdude9488]

@@jamescarbon3853 Everyone gangsta till you see one of them doing the ali shuffle

[@SapoWeonN300]

Noted

[@bingbong6176]

@@builderdude9488 AI could probably learn to showboat too if you give them enough time lmao

[@JTKatz07]

This was strangely motivating we all start off stumbling but over time we learn and grow I’m glad these two stickmen can now box

[@marklondon9004]

Now I want to see an AI version of Robot Wars. Well described combatant rules, unlimited training. Last Bot standing wins.

[@techpriest4787]

I fear it may turn into pay to win because it's expensive to train NNs. Those with the money could train far faster and therefore get much smarter AIs.

[@marklondon9004]

@@techpriest4787 good point. 200 hours on a cloud standard set up then. I'm hyped to see a dude find an iron skillet and ko the opponent.

[@samobrien815]

bring back Bamzooki!

[@femimark5021]

@@techpriest4787 tbh with you I don't mind I want to see the best

[@joshuadelaughter7968]

Like Battletech style? That'd be cool.

[@oldmandoinghighkicksonlyin1368]

AI has learned to never interrupt when its opponent is making a mistake.

[@mho...]

well that would be unfair, wouldnt it?!

[@jammbo8663]

@@mho... it's boxing. if someone makes a mistake, are you going to let it slide and risk losing? or would you take the opportunity

[@jaujud]

@@jammbo8663 would you capture it or just let it slip?

[@jaujud]

@the coder mom's spaghetti

[@felipo_galaxy1853]

@Sturmfrei to drop bombs, but he keeps on forgetting...

[@HeWhoLaugths]

Having taught martial arts for a few years, it was surreal seeing how the ai was moving at different stages of their learning process. It looked remarkably like someone actually learning to fight.

[@alexeibenhauss7217]

The rear hand/power hand should offer an increased reward (just like a real cross offers increased power and damage if it lands) over the jab hand to stop it from becoming a stiff jab stalemate every exchange, and having fighters with slightly different dimensions as many others have said would also be a good change

[@ElectricFuture]

Should’ve taught Tyron Woodley some of this

[@maltheri9833]

Like the throwing punches part.

[@hrushikeshgangane9803]

@@maltheri9833 tron is trained to 200mil times only, de does dancing part Allright

[@kovenmaitreya7184]

lmao! 🤣

[@ayoubmerzak1733]

Tyron's agent didn't learn to throw the knockout punch

[@ThegodisAbraxas]

What a time to be alive

[@VHenrik007]

As a fencer I'm really looking forward to what will it really evolve into. Just like when AI started becoming better in chess, we learnt a lot from them, and I believe same can be applied to more physical sports. What a time to be alive!

[@unknownr3802]

the thing is that you can actually learn loads from AI, you can literally makes one live infinite lifetimes just to do one thing, the only problem is most of them create some glitch that is impossible for humans to do lol.

[@yevgeniyvovk9788]

@@unknownr3802 then improve the physics of the simulation and the limitations of the bot so it approaches reality. But you do have a good point. Turn based strategy games are somehow fundamentally different than sports for learning from AI

[@unknownr3802]

@@yevgeniyvovk9788 that is true, i saw a paper one time where it was sort of physics based, it had joints that get locked after a certain angle etc but the machine found a way to glitch the joints into spasming the joint then flying the machine into a certain direction, then the machine learnt how to control where it got flown to, so sometimes even adding more physics and limitations actually help you robot glitch it, but you could definitely improve it to some degree.

[@aminmw5258]

We can learn from AI by their decision making capability not their executions. They will be perfect in term of executions or find glitches in the simulation That is why we can learn a lot from turn-based game. Talking about decision making, sports have been using data science for quite sometimes now.

[@creestee2229]

I'm so sorry to hear that ur a fence

[@nahhfam7678]

It's interesting as the style the simulation parameters create is quite accurate for a certain type of fighting. I assume the instructed goal is to touch against the opposition's head and not get hit by the way they are moving is very remniscent of points based boxing jabs but more accurately the probing stages of bare knucklefights where the consequences of getting caught by grazing hits is much worse so lunging and swinging back is a solid strategy when you can win with stiff jabs.

[@chrismullarkey3181]

This is the second video I have seen from Two Minute Papers. Excellent cutting edge content. Well done.

[@VR_Wizard]

Now we can recreate a virtual Colosseum the Romans could only dream about with animals, humans and even aliens fighting against one another.

[@ethancooper1056]

@Siss Derella nah I want the Virtuasseum

[@iigalaxyii9928]

@Siss Derella “AcT LiKE aN InTeLlIgEnT sPecIeS”

[@Anon-nv7bp]

@Siss Derella because violence is human nature. it is in our blood, there is nothing to "overcome". millions of years of evolution has made us, and there's been a lot of violence in that time. in fact, those who were weakest and incapable of defending themselves were weeded out.

[@pot_ato1234]

@Siss Derella laame

[@lets_see_777]

@@Anon-nv7bp "because violence is human nature." No, survival is human nature just like any other animal. Humans do not wage war because they enjoy murdering and getting killed. Its to acquire resources for survival or just greed.

[@ntwadumela_jadu9747]

Kind of crazy to hear that they only use 90 Seconds of motion capture data. Too bad you don't have 90 seconds of Bruce Lee motion capture data. Be interesting if old movie footage could be used as motion capture.

[@juliandarley]

in fact being able to use general video footage would be fantastic. one could teach avatars to dance on their own, walk down the street on their own - interacting with each other to create background street action. imagine the same for a huge crowd or a restaurant scene with waiters, diners, baristas, etc. creating all this background action is very expensive yet improves the believability of a story greatly. fine if you have the budget, not so good if you don't - until we avatars like these. the possibilities may soon be limitless.

[@albertnoble2727]

You can re-create it as motion capture data, or maybe use AI to turn it into motion capture data but handrafting would be better with today's technology.

[@Ben-rz9cf]

It can. As long as the footage is full body and high enough resolution and we can ai upres it then derive motion capture data from simple video

[@noblebuild2550]

Someone should choreograph his moves in slow motion and speed it up infinity to match Bruce Lee's speed

[@leonfa259]

It may be possible to skip the motion capture data and just train longer

[@joesomebody3365]

Would love to see a future where AI in video games can dynamically adapt to what your doing, hopefully without them becoming impossible to defeat.

[@tatsuke-sama3946]

I see a rise in controller buying

[@zsomborszepessy4351]

thats already happening, been happening for a while now actually

[@hxhdfjifzirstc894]

That would be interesting... a video game that gets harder, the more you play against it. I think this would really help people to learn strategy.

[@frankjaeger1711]

⁠​⁠@@zsomborszepessy4351I know of a few games that have that adaptive difficulty, but it’s usually a mechanic and not ai actually learning to kill you. I know in Tlou for example, enemies will flank you while others will aim at where they think you are until you make a move. So many times I’ve panicked when that would happen so I thought I could be quicker and headshot an enemy, but they have the advantage already aiming at me so I get hit 90 percent of the time. Enemies will also learn to try and stealth attack you especially when they’re the last ones standing. I know games like stalker and the old fear games have some of the best ai, but idk how well they adapt to what you’re doing. The ai in tlou 2 is really tough on the hardest difficulties, but I think that’s mostly because they basically have aimbot. If I’m in their sights, they will almost always headshot me no matter how much I’m moving. You have to basically catch them by surprise since most head on fights will be game over.

[@PazbiZavatzki]

Excellent video. Really interesting to see the different levels of improvement and the "hypnotism".

[@BaronVonScrub]

As an ex fencing coach myself, I was watching the boxing component going "Those lunges look more akin to epee fencing". Sure enough, 10 seconds later it's applied to fencing, albeit foil hitbox. Very interesting stuff. Maybe my combination of fencing knowledge, gamdev and machine learning could have some niche crossover here. Hmm. Edit: One major difference I could see is that the swords in this simulation didn't flex the way regular ones do, and particularly using that foil hitbox, that leads to extremely linear plane along the direction of the piste. Giving the AIs the ability to flick the blade with the appropriate movement and inertia would lead to far more dynamic fighting, since there would be an incentive for that lateral motion. Better still would be this for simulating epee, since it makes sense to disregard the foil's priority rules. In which case they would need the bell guard protecting the hand, which would be very easy to add to the simulation. Giving the AIs both the ability flick the weapon over the bell guard the way humans do, and the reward of doing so, would lead to more realism - and also clear the way to more high stakes combat options, like rapier to first blood.

[@twicevictorious8828]

Dude if you could design a game or simulation with that fencing experience and knowledge I'd play the hell out of it even after quarantine

[@jinjinjinrou]

@@twicevictorious8828 you should try Hellish Quart in the meantime.

[@amegatron07]

Well, you can still try to make a decent bot for your potential VR-game.

[@BaronVonScrub]

@@twicevictorious8828 Sorry, I just saw this. The primary issue with taking it to VR is that there's no proper haptic feedback; the collision of the blades for parrying, beat attacks, glissade, etc is pretty core to the sport. Additionally, even if you could manage that, you'd want it on a system that can fully track your whole body, otherwise you couldn't specifically move parts to dodge. :)

[@aurelienyonrac]

Thank you

[@danisaksson3214]

I want to see this in games with dynamic outcomes for side characters. It would be awesome to also somehow be able to help improve their potential by helping a character, giving it access to a few more million steps of training data or something like that :3

[@oldmandoinghighkicksonlyin1368]

So instead of the side character walking into walls, it just falls down immediately.

[@yevgeniyvovk9788]

so like pokemon, but instead of food giving it preset level powerups, the in game food lets your agent train for 250M more steps. BRB opening up unreal engine

[@LunaticCharade]

would be super cool yeah. One bit that is a bit.. a bit of a pity is that both seem to have the same model, would be very interested to see how they would perform toward opponents with different tactics etc. then also for your game idea, you can choose not only your favorite to train, but also who they train against!

[@_.Dylan._]

@@yevgeniyvovk9788 Oohhh that sounds really cool

[@yevgeniyvovk9788]

@@LunaticCharade like boxing archetypes: southpaw, counterpuncher, ect... great idea

[@granpatriarca3726]

3:33 Those bots fights like my drunk neighbors. btw which language and engine used to make that?.

[@PhycoSerpentStudios]

I would love to see a video where you teach the ai different fighting styles and then had them fight other styles to see how they would adapt over time

[@Fermion.]

That would be a great training tool for MMA professionals preparing for a fight. Not sure how hard it would be to incorporate grappling and submissions though.

[@laserfoxultrabeam]

"and, you know what's coming?" Boxing AI vs. Fencing AI?

[@oldmandoinghighkicksonlyin1368]

AI MMA.

[@theaveragepro1749]

Fencing AI will probably win because of it's reach, historically weapons seem to be an advantage.

[@nonamenoname1942]

... vs. Gorilla AI. (Mortal Kombat's fonts) FIGHT!

[@nitfitnit]

Alien AI vs. Predator AI

[@nitfitnit]

@@nonamenoname1942 Finish Him!!!

[@jofx4051]

After 10b steps the AIs learn to just abandon the ring and go to bar and called it a day

[@vancerain100]

2:32 my boxing teacher when I not ready for practice in 1 minutes fr

[@nyeti7759]

Fascinating video, well produced and presented with a nice bit of understated wit. Thank you!

[@user-cd4bx6uq1y]

3:15 a man of culture I see

[@Wecoc1]

To be fair, if I'm playing that game and the opponent breaks all their bones at once I'll also forget about trying to cross the line

[@HenreBotha]

1:13 In fighting games, we call this "conditioning" the opponent. We train the opponent to react to an action in a certain way, and then we punish them for reacting in that predictable way.

[@honyokgaming5601]

0:15 i don’t know why but this section made me laugh so hard

[@FoodUsedToBeNice]

Bro this so meme

[@MineSweeper-bg8un]

0:45 RED used 'Curl into a ball'! It was super effective!

[@billy4734]

2:47 live simulation of the Logan Paul match

[@jimbobur]

The first example is more of an illustration of the limitations of the model rather than of it uncovering some special "hypnotising" technique.

[@ska8terdude2]

This is so exciting for someone like me who loves VR boxing games. They’re great and all but the enemies just aren’t dynamic enough to keep it interesting for long. Can’t wait till this is realtime!!!

[@alansmithee419]

The fighting is realtime. It's the training that took ages. Once it's trained it can be used for whatever you want almost instantly.

[@unliving_ball_of_gas]

@@alansmithee419 That's the problem. I don't think 1B steps of training-data could fit in a tiny phone-size storage.

[@alansmithee419]

@@unliving_ball_of_gas You don't need to store 1B steps of training data, you only need to store and run the final AI. The training will have been done pre-release of the game. After that you don't need the data anymore.

[@unliving_ball_of_gas]

@@alansmithee419 Huh, that's how it works? Because I have this game "Evolution" basically you build a body and a neural network and it'll train itself to walk, run climb up stairs, jump, etc. and the more you train it, the laggier it becomes. You could download the game on mobile/pc if you like. Edit: The name is "Evolution" by Keiwan Donyagard

[@iruns1246]

@@unliving_ball_of_gas Optimizing a trained model is a whole other thing. Yes, if it's not optimized it will become so laggy to run in ordinary computers. I don't think that Evolution game has good (or even any) optimization process.

[@HarrySuh]

It would be interesting to see how these AIs develop different strategies for different physiques. Different height and reach would be pretty simple to implement.

[@metafisicacibernetica]

I JUST LOVE THIS! TY SO MUCH!

[@TheRealBDouble]

I LOVE the AI fencing. I've fought Historical European Martial Arts and SCA heavy rapier/cut and thrust for 20 years, so I think it's really cool to see the AI learn how to sword fight

[@PritishMishra]

1:43 Me before I even start studying

[@joshuadelaughter7968]

1:00 When AI is so good it figures out how to use exploits.

[@SuLokify]

That's a pretty common thing for ai trained to play video games

[@joshuadelaughter7968]

@@SuLokify Yeah. I'm thinking devs could use this to help find bugs.

[@joec7130]

There’s something hilarious about that blue man trying to run past the red one. It’s like he’s spawned in and immediately starts frantically sprinting like a cartoon character 😂

[@SomeAutomaton]

This man has just taught an AI how to beat the daylights out of something, so beautiful

[@farmanshaikh6405]

around 3:28, they really start to exhibit true point scoring strikes, as well as counter punching. Really impressive.

[@silversrc]

I cant wait until we can watch AI Boxers box , or create our own AI and challenge other players AI, with different fighting styles. it doesn't even have to be limited to boxing. man that would be so cool

[@draganandrei5356]

That'd be really cool

[@ShawnJonesHellion]

as if real ai is allowed to exist

[@kingdweeb5065]

There's something similar in starcraft broodwar's SSCAIT. Give it a look!

[@Rctdcttecededtef]

Epic major scale fighting simulations

[@mithshude]

@@ShawnJonesHellion real AI will exist, mainly because governments don't understand the dangers. in the words of elon musk: i tried to get people to slow down AI, to regulate AI, this was futile. i tried for years. main reason he's working on neurolink btw. if you can't beat them, join them

[@medea27]

Stage 1 of boxing looks like someone snuck into the lab & cheekily programmed the AI to think that it was a Jedi Master that could vanquish it's opponent by simply staring them down & using the Force to knock them over.

[@RyanJosepher]

It's like I'm learning how my brain works on a different level. This makes me so freaking excited for the future. I like how the red agent learned how to play dead or learn reverse psychology at a very base level

[@AllanMcKay]

So amazing! Thank you for sharing Karoly, just watching them essentially 'learn to walk' is inspiring enough. So amazing watching this stuff! Thank you again for this video!

[@luuketaylor]

2:01 "I am afraid this is just passing out without any particular benefits." Huh. I have a few friends who I can say that about...

[@meditativeturtle]

In one week... What took us, humans, our whole existence. Awesome and also a little bit concerning. I loved this video. Bravo! Saludos desde España!

[@amegatron07]

Actually, I would on the contrary be surprised if the researchers stopped at 130M steps. The reason was mentioned: the agents didn't even had a clue that they could get higher rewards by touching the opponent. So it was mainly a matter of random to start doing so, but until that it would be quite unreasonable to quit. But as always, it was still amazing to watch how did the imitate boxing :)

[@PeterBarnes2]

Looks like the Toribash characters. Wonder if they could put the two together, either with players fighting against these AIs or providing training data for the AIs.

[@alfredogonzalez2576]

Hey, do you know what is that? I thought it was Toribash, but it isn't, how can i test the AI in there?

[@PeterBarnes2]

@@alfredogonzalez2576 You'd have to check their paper, but I don't think it's Toribash.

[@CameronKujo]

@@PeterBarnes2 it’s not toribash. And if it is, it’s an old model. I can’t believe people still play the game. Props

[@PeterBarnes2]

@@CameronKujo I haven't played it in ages, I just remember the very distinctive models. I didn't think they were the same, but they look similar, and I was more wondering if they would be compatible enough to quickly retrain the AI for toribash.

[@TheLegendaryHacker]

Goddamn, I haven't heard the word 'Toribash' in years.

[@HebaruSan]

I recognize the glove-to-glove dancing in a circle as resembling a real heavyweight boxing match

[@Taygon45]

Yo! I think I've accidentally done the Adversarial thing before in Smash Bros. I forgot the stage and characters, and it was only for the first second of the match but I always did something that could be normalized, AKA something that I could buffer to do pretty much frame perfect almost every time. And I realized my AI opponent was also doing the same thing every time.

[@bacabc8096]

Would be interesting to see several ai bots put in a incredibly hard puzzle game where they need to cooperate to win.IT also will have this physics engine ofc and would be hilarious.

[@getdavemoore]

2:58 the Eureka moment :) amazing result! @Dr - i love the way you've told the story of the process here. In your next vid, could expand on what form the 'reward' takes? I get in principle how this strengthens the neutral path, but what is the general math to it? Thanks for your great work covering these paper dropping advancements ;)

[@davidinark]

I live watching AI “learn” what to do. I also like that you include previous research so that we can come along on the journey. Excellent work, as always!

[@BevansDesign]

Lately I've been wondering about how long it's going to take before characters in video games are able to move realistically like this, rather than using premade animation cycles and other "shortcuts". This video talks about the millions of steps in the learning process, but once the learning has gotten to a sufficient place, can that movement "model" be applied to characters in a game? Is it versatile enough for that? Or is the issue more about processing power?

[@chip7753]

probably like 5 or 10 years i would say.

[@realcoolguy123]

you could probably train an AI to create realistic movement animations, but integrating an ai just for character movement is out of the question. It would be way too resource intensive and highly inefficient.

[@ttracemusic]

Literally one of the most interesting videos on youtube!

[@larion2336]

1:19 This is what we call a feint. Pretty awesome that the AI figured out this concept, albeit a kind of ludicrous version of it.

[@PhilippeLarcher]

it looks like high level (or bullshit who knows) Systema

[@Ratkill]

Hope there are follow-ups on this. Very interested to see how the AI moves with a bit more parameters, like requirements for the acceleration of the strike, or achieving a peak transfer of inertia. I wonder if the simulated weight of the limbs was especially accurate, it seemed that way. It would be amazing to see how the AI moves to deliver and avoid perfectly applied striking. Cool to see that in a lawless sandbox, the real world method of movement is still validated.

[@wormemc]

So glad I found this channel . This is so monumental, won't be that long before some weird shit happens.

[@Thirzy]

it would be really cool if there were an array of different fighters with different proportions to see which ones beat which and how they adapt

[@toxiccan175]

We’re really setting the stage with this. Now Terminator won’t need to steal a weapon upon arrival!

[@youtubeuniversity3638]

"Learn boxing and even mimic gorillas" Punch-Out Reboot spoiled the secret boss again.

[@walugusgrudenburg3068]

Is it really spoiled? We all knew it was gonna be DK again.

[@IvanSensei88]

Would've been cool if they 'saved' the AI after each X steps, and then have them fight each other, just to show how drastically the AI improved and how hard it can demolish its previous iterations.

[@Mr.McWatson]

"This is just passing out without any particular benefits" hahaha I don't know why but I loled

[@ReynaSingh]

Another impressive step forward. Keep up the good content

[@funny-video-YouTube-channel]

They learned to dance faster than to do boxing. Should have kept learning the dancing moves, then it might have been more fun !

[@michaelj9153]

0:45 I would be extremely impressed if a human thought of that but an AI thinking of something that clever is on a whole different level of impressive!

[@cem1056]

The explanation about the hypnotic adversarial collapsing sounds like something that would happen in Baki

[@falxie_]

It'd be amazing to see them have more than one strategy evolve

[@genericytprofile852]

It's freaky how close to real life movements the AI can get. You could of honestly said that footage was mocapped and I wouldn't have argued. Imagine if we instructed it to fight using weapons, or even group fighting! The possibilities are really endless..

[@watchm4ker]

That's at least partly because motion capture was used as training data.

[@flance911]

0:15 wow. that's my skill of boxing... perfection from the start, how it can be improved

[@violatorut2003]

Really reminds me of Sumotori Dreams. So much fun playing that game.

[@martyscodingpalace8609]

What a time to be alive

Humans hate being told the optimal path. So telling them the optimal path isn't the optimal path.

[@lewischristie2285]

there are no truly optimum tactics in football. the game is fluid and players adapt strategies in real time based on the situation theyre faced with in that moment.

[@ezequielpro08]

Really Excited for the future of the robots! This can be used for security? Or maybe for a box training? What a time to be alive!

[@EricNahuelJurio]

Impressive foot work

[@Alex-qd7ly]

Wow… truly fascinating!

[@diveinnjim]

"What a time to be alive" loving this, great video

[@Gorguruga]

The AI get into an interesting jab war but I wonder if it's because both characters have exactly the same dimensions or are they marginally different? In real boxing, opponents can be different shapes and sizes with variable arm length, height, reach, punch range, speed, stamina etc... If you had two such AI of different dimensions, perhaps the fight would turn out differently as the AI which is getting out-jabbed might change it's tactics completely?

[@hereandnow3156]

Could also be due to the physics simulation. It seemed like if the models swung too hard they would take themselves off their feet so maybe the model found that the best solution was to just go for light jabs

[@pablom3162]

this is some of the best content I've seen in while

[@hexagerard]

Would be nice to see an IA trained with short arms vs another with longer arms. Both with the same weight, but different distribution of mass in the body

[@kiyabcs]

It would be really neat if you could program each AI model with a different boxing style.

[@antoniodiverso6191]

I'd really love to see the fencing one, being a fencer myself it got me hype af

[@Metallicity]

Squaring off in the ring, staring their one another down,waiting until someone collapses from exhaustion alone? Now that's some gentleman's boxing as Andre Filipe originally intended.

[@fighthighlights2201]

What a time to be alive!!! 4:10

[@bhante1345]

This going to make for some great ambient drum and bass mix b roll.

[@trashman1358]

"This is just passing out without any particular benefits..." That statement is absolutely priceless!!! Lolz!!! XD

[@davemarcosmalicdem9543]

Ooh, Filipinos are gonna love this! We really love boxing! What a time to be alive!

[@Urge-To-Burn]

“You can box anyone you want, all you have to do is practice.” - Pablo Picasso

[@lecoutcritique8854]

The AI wasn't doing nothing, it was already mastering the art of No touch KO :D

[@Breakbeat.]

4:45 This is obviously the future of combat sports. We just don't understand how overpowered this technique is yet, but we will....

[@dr.doppeldecker3832]

Imagine in the future we have MMA fights contested by AI:) i would love to see that!

[@oldmandoinghighkicksonlyin1368]

Me too

[@vladimirdyuzhev]

No, too boring. There is no pain, and so no overcoming the pain, and so no excitement.

[@GuacJohnson]

@@vladimirdyuzhev spotted the casual

[@Lee-pf6od]

Seeing previously unknown strategies would be exciting, just as we saw AlphaGo come up with novel strategies. Masters of those games have even stated it's often more interesting to watch the AI matches, than the more familiar/predictable human matches.

[@dr.doppeldecker3832]

@@vladimirdyuzhev you could easily program pain, health, stamina etc.

[@ECReeves]

idk whether to be amazed or terrified lol. I understand the beauty of this but consequences seem inevitable. I would be stoked to see video games AIs have systems to truly learn player behavior and other ai behavior that would be incredible

[@threemooseqateers9689]

Hi two minute papers! My buddy and I loved this video, and wanted to try to use the AI at 1:30 ourselves. Is this AI available to the public? I'd even be happy to pay for it. It's some wonderful tech, and we want to see if it is possible to use such a clearly intelligent AI in a setting where a person could interact with it directly.