DeepMind’s AI Trained For 5 Years... But Why?
Переглядів 385,239
Рік тому❤️ Check out Lambda here and sign up for their GPU Cloud: lambdalabs.com/papers
📝 The paper "From Motor Control to Team Play in Simulated Humanoid Football" is available here:
www.science.org/doi/abs/10.11...
arxiv.org/abs/2105.12196
My latest paper on simulations that look almost like reality is available for free here:
rdcu.be/cWPfD
Or this is the orig. Nature Physics link with clickable citations:
www.nature.com/articles/s4156...
🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Aleksandr Mashrabov, Alex Balfanz, Alex Haro, Andrew Melnychuk, Benji Rabhan, Bryan Learn, B Shang, Christian Ahlin, Edward Unthank, Eric Martel, Geronimo Moralez, Gordon Child, Jace O'Brien, Jack Lukic, John Le, Jonas, Jonathan, Kenneth Davis, Klaus Busse, Kyle Davis, Lorin Atzberger, Lukas Biewald, Matthew Allen Fisher, Matthew Valle, Michael Albrecht, Michael Tedder, Nevin Spoljaric, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Rajarshi Nigam, Ramsey Elbasheer, Richard Sundvall, Steef, Taras Bobrovytsky, Ted Johnson, 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
Károly Zsolnai-Fehér's links:
Twitter: / twominutepapers
Web: cg.tuwien.ac.at/~zsolnai/
@TEMPLERTV Рік тому
A few years ago you helped ignite my passion of machine learning. Since then I’ve learned to code, have educated myself vastly in machine learning. I’m currently building my own small NN. Thanks for opening my eyes to something amazing
@TwoMinutePapers Рік тому
That is absolutely amazing, so happy to hear your story! Hope the neural network will go on to do great things!
@HiddenExp Рік тому
@@TwoMinutePapers You are big my fellow scholar
@bubbleboy821 Рік тому
The first time I learned about them was SethBling'd Mario NN
@Litwinel Рік тому
@@TwoMinutePapers this must be a great feeling to know you are an inspiration for others
@electron6825 Рік тому
@@ThatGuy-kz3fx neural nutwork
@Makmarian Рік тому
It would be cool if there were simulated sport competitions where teams used their own AI model against each other
@raylopez99 Рік тому
They do this already with chess, computer chess competitions, the latest winner is AlphaZero-based Leela, just beat the reigning champ StockFish.
@SpaghettiToaster Рік тому
@@raylopez99 Didn't Stockfish win?
@TwoMinutePapers Рік тому
Loving the idea.
@cosmos3576 Рік тому
I would like to see this also in FIFA.
@sebastianjost Рік тому
There are competitions like that. Not sure if there are any for sports, but I've definitely heard of some other competitions: - Minecraft village/ city generation AIs - Minecraft resource gathering AIs (get diamonds etc.) - Ticket to ride AIs (board game) - bad piggies/ angry birds AIs (not sure which one) - chess AIs ...this is what I remember without actively looking for them. If you look for competitions like that, I'm sure you'll find some.
@anthonybernstein1626 Рік тому
To get a feeling of how difficult this is: imagine QWOP with 56 keys instead of 4, and you don't just have to run but to play football, in 3D instead of 2.
@dzambi Рік тому
@@eetm but your 🧠 is just a processor playing 3d qwop in the dark.
@InceyWincey Рік тому
To get a feeling of how difficult this is, try to consciously control all of the muscles that are required to walk. Or just appreciate the fact that your brain can do that for you while you think about more important things.
@sfurules Рік тому
@@dzambi I didn't expect this level of existential crisis on a chill Sunday....
@jamqdlaty Рік тому
Also the buttons are pressure sensitive. ;)
@spizzleyo Рік тому
All things should be related to QWOP
@jordyp3696 Рік тому
they should do this with real rules (throw ins and cornershots etc), and with 11v11, run it for weeks on different computers, see if they come up with some kind of great strategy, see what formation and stuff they pick.
@letMeSayThatInIrish Рік тому
And add stamina so they have to learn to economize their energy.
@softwarelivre2389 Рік тому
And goalkeepers
@alihms Рік тому
And a referee.. who always seems to be one sided too for the real effect.
@user-eg7cz1oq9m Рік тому
@@letMeSayThatInIrish yeah... genetic, height, weight, heart illness, traumas :D
@nobodyishere Рік тому
@@alihms lmao
@miladragon Рік тому
I notice that they still seem to move really unnaturally -- their upper bodies seem very flail-y. I wonder if that would get ironed out if they were given some cost to excess movement (just like humans get tired).
@Saotik Рік тому
I was just typing something similar before I saw your post. I even used the word "flaily". Adding fatigue to the simulation feels like it might have significant impact.
@budnick1 Рік тому
Along similar lines, if there was some cost to getting hit, like being slow to move for some time, I wonder if there would be an emergent consensus to avoid causing damage to your opponent, like an emergent moral code. Would they even develop a tit-for-tat rule enforcement?
@nemonomen3340 Рік тому
I was also about to say this. It seems to be a commonly overlooked issue when training AIs in movement.
@maelstrom2313 Рік тому
They may be moving more efficiently than real football players. People don't always take the most efficient paths when moving, we have to consider extraneous social variables of how our movement looks. It's possible that it takes more energy to restrict the movement of limbs than to incorporate their inertia into the body's trajectory.
@miladragon Рік тому
@@maelstrom2313 if that were the case, real soccer players would move like this. No one cares about looking stupid if they win (cf. the Fosbury flop, which looks stupid but is standard, because it lets you jump higher). There's also no reason to think that these should be moving efficiently, because there's no incentive for them to be doing so (they don't get tired).
@Quazlyy Рік тому
I think the pre-training behaviour pretty much captures the behaviour of actual football players
@vasekbrezina2801 Рік тому
Exactly :-)
@brooksgunn5235 Рік тому
I was gonna say 😂
@theinacircleoftheancientpu492 Рік тому
Ah, the bugs kick in sometimes.
@vixantenna Рік тому
From the expert opinion of someone who's never watched football before
@JH-ji6cj Рік тому
@Vixan knowing football, but not acknowledging flopping from a foul? Who doesn't watch football?: you
@jhunt5578 Рік тому
It's crazy how the AI just iterates and comes up with through passes, lobs and cruyff turns.
@jakab174 Рік тому
i am a little bit sceptical, with this, there are probably thousands of hours of footage and they show the best most human like stuff, these are things that just comes from the noise. If the ai would be any good they would shoot the ball directly to the empty net every time, then it would learn its better to put one player to the goal
@yousuck6222 Рік тому
@@DailyCorvid You dont need a ref with robots. That's the point.
@SP-ny1fk Рік тому
Imagine training an AI to do a task for 100 years in 10 minutes, then exporting it and importing it into a robot to achieve the task perfectly in the real world What a time to be alive!
@spinninglink Рік тому
Think i saw something about them doing that with a ping pong machine, right?
@CircuitrinosOfficial Рік тому
I wonder if they inject noise into the simulation to simulate the imperfections of reality.
@derekofbaltimore Рік тому
Your point holds but i dont think that doing things in simulated world corresponds 1 to 1 with the real world. It would still need lots of training in real world (because the simulated world wouldn't hold all the variables that the real world holds and those small inconsistencies add up)
@josesandv Рік тому
I have always ponder that if our universe is simulated, maybe it is in a supercomputer that does million of iterations, where every iteration takes milliseconds but for us is eternity
@el2746 Рік тому
@@josesandv More like every millisecond does millions of iterations
@rogueyun9613 Рік тому
Honestly the first one where all the players are writhing on the ground looks pretty accurate to me.
@KangJangkrik Рік тому
Seizure?
@KuZiMeiChuan Рік тому
@@KangJangkrik The other team hit me.
@dranirbanpal Рік тому
Yes, that's advanced training on what to do after a foul
@vibovitold Рік тому
neymaring the shit out of the game
@Soupie62 Рік тому
If that was truly all you need do to play, I might stand a chance of qualifying.
@monocore Рік тому
I see some serious meme potential in this
@FenrizNNN Рік тому
We can make a religion out of this
@MarcillaSmith Рік тому
What is the game the AI is playing? It looks like non Americans trying to invent their own version of football 🏈
@LinggarMaretvaCendani Рік тому
@@MarcillaSmith Why do you call it football when you bring the ball using hands? Shouldn't it called Handball?
@speedfastman Рік тому
@@LinggarMaretvaCendani No it should be called soccer cuz it socs.
@MarcillaSmith Рік тому
@@LinggarMaretvaCendani handball is when you can't afford a racquetball racquet.
@JakeHaugen Рік тому
This actually could be a really cool esports team. Like imagine if madden had AI agents to play the team. It was actually pretty entertaining to watch.
@michaelatorn8380 Рік тому
I see great potential in deadly sport types played by AI.
@zapdart1803 Рік тому
Worth checking out altered state machine and their upcoming games (FIFA AI League and AIFA)
@Ulexcool Рік тому
Nah
@MrUbister Рік тому
@@Ulexcool Hater
@brendanrodgers9753 Рік тому
@@michaelatorn8380 any examples of what sports specifically, can't think of any other than extreme diving
@818suki Рік тому
Even after all these years, you still amaze me with how understandable you make these papers for people like me. Thanks for really spending time in digesting this information to someone who's not in the field or can't allocate enough time to dive deep.
@TwoMinutePapers Рік тому
You are too kind - thank you so much! 🙏
@manofsan Рік тому
*Imagine a Zombie movie/show where the zombies first start out writhing on the ground, and then quickly they learn to get up and walk, and then run, etc, etc*
@vibovitold Рік тому
and once the movie credits start rolling, there's Pink Floyd's classic playng in the background "...Hey, teacher! leave them kids alone..."
@thecousindeci1103 11 місяців тому
bruh thats a really cool idea for a game. The longer you live the smarter the zombies get with ai, honestly it would be scary as shit when they all learn to run and look for you in houses. Something like project zomboid but at some point the zombies learn to coordinate.
@BryceRogers Рік тому
It would be cool to watch the 50 days AI vs the 3 days just to really show the improvement.
@zodywoolsey Рік тому
I would absolutely watch videos of a bunch of ai players fumble around like this for hours.
@devfromthefuture506 Рік тому
Me too and I would like to ask where I can find more videos of these
@zapdart1803 Рік тому
FIFA AI League is releasing in less than a month. You will get your wish
@aaronconnolly1496 Рік тому
Just go outside man
@smolbrainstudio Рік тому
gold
@otto-pi8xu 6 місяців тому
I need this to become a thing, like using real football matches to train the AI and have simulated matches between real teams based on how they play. I would love that.
@xAgentVFX Рік тому
I want more Ai Football!!! I wanna watch a full match! Looks so fun. Imagine what they might do years from now??
@DudeWatIsThis Рік тому
8:22 **gets lightly tripped over, falls down and has pain seizures** The most realisting thing in the entire video.
@lGNITED Рік тому
Two Minute Papers, thank you so much for providing us such incredible content.
@larryking6259 Рік тому
Thank you especially for comments on those graphs. Big respect!
@sithmaster Рік тому
Just imagine the labour curve going down suddenly after a couple of weeks… nobody knowing why… and AI looks like it would start to discuss and talk to each other on the field rather than playing. THAT would give me goosebumps. ;D What a time to be here.
@OperationDarkside Рік тому
Boston Dynamics vs Real Madrid when? Also I want to see 100 vs 100 players and if this can be transferred onto soldiers like in Totally Accurate Battle Simulator.
@usm1le Рік тому
realistic human movement that follows the laws of gravity and moves on its own has always been fascinating to me
@JanBadertscher Рік тому
I would love to find out with a model like this what the ideal play style would be according to game theory and physical limits of the players, but still having to follow all the rules. For example: Would it actually be better even for the goal keeper to move out and play in the field, vs. staying in the goal? I guess humans didn't figure out optimal gameplay yet for soccer and this could lead to new and crazy strategies.
@SweBeach2023 Рік тому
It was my initial thought as well. Using AI we could try so many new strategies. And it wouldn't be hard to give the different AI players different properties to reflect the properties of the real players of a professional team. On eis a faster runner, another have better stamina, a third one have great control of the ball etc.
@mason4295 Рік тому
2:11 "Holy mother of papers!!" hahahaha love it. Great videos and papers 🤖
@Plafintarr Рік тому
My heart desires a whole tournament with these little AI's. Crazy ragdoll physics and wild flailing bodyparts included. They are so fun to watch! Can you upload more footage?
@ianbot Рік тому
How epic is it gonna be when a fellow scholar makes a soccer game like FIFA but using these AI's
@zapdart1803 Рік тому
FIFA AI League game is about to be released on the App Store
@nontypicalguy Рік тому
I'm fascinated by the game AI Roguelite and stuff like this video, so I'm subbing now - Look forward to seeing more of your content!
@theflashevo6137 Рік тому
Wow, this video showcases the impressive capabilities of DeepMind's AI technology. The ability for the AI to learn and adapt to the complex rules and strategies of football in a simulated environment is truly mind-blowing. I can't wait to see how this technology will be applied in the real world and the impact it will have on the future of sports and beyond.
@connoraugustine2127 26 днів тому
This is the kind of niche thing that I personally really enjoy reading in my own time, but it's so much better when you have a PhD holder narrating for you and showing you all of the nuance that you might have missed.
@thomasrosebrough9062 Рік тому
0:53 me when mom says I can't have another pack of fruit gushers until I eat some broccoli
@SMASH_REVIEWS Рік тому
HOLY MOTHER of Papers,... Hahaha Love u Man.
@Enceos Рік тому
I wonder if it's possible to train certain skills first, like getting up, sprinting and kicking separately, then continue with the game training.
@bradleyandrews2444 Рік тому
these little foot ball player are so fun to watch i could watch that for the whole day
@mjpunited5727 Рік тому
Physics agents are so interesting, I wonder if there is any demo of this that I can find so I can run it myself. Would love to train goalkeepers and play 6v6 or even branch out to something like fencing!
@chrisfaulkner9355 Рік тому
The way this dude pauses to extend EVERY diphthong. A-and. So-O. No-O. YE-es.
@nolikeygsomnipresence270 Рік тому
Absolutely fascinating. Thank you
@petermoras6893 Рік тому
I think one of the major improvements in the last few years we've seen in AI training (besides training size/time) is how we train intermediate goals to speed up training. If we simply took the untrained AI with the joint body, and asked them to learn soccer, it would take forever with minimal improvement. But as we've seen in this video, they first train the AI to enable it to walk, dribble, and kick the soccer ball. Once the AI knows how to perform general ball handling tasks, it can use that understanding to more quickly learn to score goals. This might just be my perception though.
@vibovitold Рік тому
the next logical step would be (and it's probably already done to some extent, in one way or another) to split the AI into a "teacher" (supervisory) and a "pupil" (learning) AI, whereby the former one would be in charge of figuring out and setting the incremental goals for the latter to accomplish
@arifdiansdocumentary Рік тому
0:56: "How much beer do you need" Him: "Yes"
@woodybob01 Рік тому
One day there's gonna be a better way to 'start' these training projects. It just seems wrong that they should start with such little knowledge. I'm sure something will arise as we work towards the future. By the way this was damn impressive! Just the mere fact that it could side-step and through-ball shows how much of an understanding it really has about the game, a surprisingly deep one!
@bingchiIIing Рік тому
@@DailyCorvid loving this
@kairu_b Рік тому
I like your storytelling, sir. What a time to be alive!
@aleksanderdl93 Рік тому
Could be interesting to set the standard conditions/physics for the match and then have two teams train their NN best possible, aftwards pitting the AI teams against each other. Wonder if there could be upsets like irl or the better team would always win
@argo2720 9 місяців тому
it would be so sick to see full teams progress and having a goalie learning how to goalie and adding in rules like offsides, out, fouls, penalties. would like to see what formations they would come up with or if they would stick with the all forward all back game plan
@emekayyi3332 Рік тому
i love your content bruh, long time fan! ölelés!
@tim40gabby25 Рік тому
Remarkable. Ex footy player here, wondering how long till these analyses show how Messi's additional value was in the distribution of labour - a 'team player'.
@ai_is_a_great_place Рік тому
I can't wait to see the Olympic AI Opening ceremony!
@pandoraeeris7860 Рік тому
I, for one, welcome our new AI football overlords.
@Plumfan_ Рік тому
It would be awesome if they can also simulate some form of fatigue, some movements look too energetic or wasteful.
@visualbree Рік тому
The through ball at 4:29 is amazing 🔥🔥
@PsychBoost Рік тому
I hope you have seen "Lawyer Explains Stable Diffusion Lawsuit (Major Implications!)" by corridor crew uploaded a few hours ago. He even uses your catchphrase at the end! What a time to be alive!
@nawtmyrealnamelol Рік тому
3:05 so cool how they visualize field control
@surajvkothari Рік тому
If this simulation gets more accurate, it could influence how football is played in real life. Imagine when the richest clubs can afford to create such simulations and optimise their players.
@bobisatelier Рік тому
they wouldn't need to be rich probably
@volkan7505 Рік тому
The talking sound so robot like. Its like you have all the words with your voice already recorded and then you just type the words which automatically creates the voice
@dillanio9191 Рік тому
They're using their body to shield the ball and then turning around to beat the pressure from opponent... Wow.. That's something one of the best midfielders of all time Xavi did often too... Incredible
@flamingosoup6375 Рік тому
I wish there was like a place I could go and watch these AI do their thing in real-time, I could watch that stuff for hours.
@drawmaster77 Рік тому
it would be interesting if they added some stamina function, so they run more realistically and not swings their limbs all over the place.
@ChristopherCricketWallace Рік тому
yeah. I would like to see the rules built-in, as well. Let the AI learn in the context of the real game with out of bounds, and penalties, corner kicks, etc.
@drawmaster77 Рік тому
@@ChristopherCricketWallace I mean this maybe overdoing it with the rules, but at least have them run more realistically not like they are spazzing out with limbs flailing all over the place lol. Maybe add some cost to limb movement which factors into their stamina bar and when stamina is low they run really slow which would affect their performance and that way AI would learn to be more "efficient". Just throwing some thoughts out there.
@AdamsBrew78 Рік тому
This was fascinating to watch. Would be thrilled if we ever get to see a similar experiment applied to mastering other sports or disciplines. Maybe have these physics bros learn to drive a little simulated race car on a very technical track ;)
@davidwuhrer6704 Рік тому
RoboRace
@MrHeliMan Рік тому
I always wanted a physics-based walking system in a videogame and although I never thought I'll be here for it, this makes me think I just might. Counter-Strike 2 where you have to be careful about how fast you're running down the stairs or walking on mud? Yes, please.
@chikita5110 Рік тому
I studied multiagents theory at university and I can't wait to see this expermient go with more players ! BTW if anyone has sources about theory of agents interactions in tthis context
@ali_dogu Рік тому
Ayo very cool video! But why does the "Division of Labour" Chart start so high? They didn't Teamplay in the beginning, did they?
@Glowbox3D 9 місяців тому
One of my favorite 'agent' training examples. So wild.
@q.u.e.r.t.y Рік тому
I would have loved to see at least a month or 2 into this. Bet I would learn something great from that
@MACHINEBUILDER Рік тому
Just imagine if this ai was put into a robot and you had to play soccer against it. It'd be horrifying with how they move - imagine if they even looked like people 💀 Still absolutely insane progress with this kind of physics-based ai agents! It's crazy!
@asrar4907 Рік тому
you do remember the part where he said that the ai trained without a refree? Gosh you need an ambulance
@davidwuhrer6704 Рік тому
RoboCup Humanoid League
@MACHINEBUILDER Рік тому
@@asrar4907 Ahha yeah you'd definitely need at least an ambulance after playing against these
@dagdbot83 7 місяців тому
I think they did that already
@SanSan-eo8rx Рік тому
Very interesting If they could also simulat the muscle exhaustion or energy usage for the movement, they could have a more efficient way of running. Because for now they run very crazy, it seems they have these kinds of mouvements from the infinite energy they have to move in the simulation. Maybe also some injury system. And of course, like mentioned in the video, a referee.
@adlwilliams 11 місяців тому
The fact that it learned to embellish an injury, only to pop right back up is great
@juliandarley Рік тому
even more fascinating than usual! this has some extraordinary implications both for AI-generated video and possibly for humans, if 'division of labour' could be translated back to humans in the form of more collaboration. for AI video it surely means we are quite a bit closer to being able to create a background street or restaurant scene and not have to animate every single crowd artiste (a nightmare). this would be hugely helpful in itself, but if/when combined with the ability to direct avatars at a high level (eg "please go and pour some wine into that flute"), it will bring us closer to being able to make virtual movies, especially for difficult or dangerous scenes, which could then be intercut with real actors.
@mstreich Рік тому
I was thinking teams could learn new approaches or possible plays.
@JorgetePanete Рік тому
"please" 😂
@GikePeterson Рік тому
2:20 We used to do the same trick when we were kids, passing over the wall when we played soccer.
@khangvinh4656 Рік тому
1:13 This is proof that not knowing how to play football can cause extreme cases of seizures.
@unclejuju12 Рік тому
6:40 its interesting how that curve looks similar to the Dunning Kruger Effect
@youtube_moderator Рік тому
Would be amazing to see this as a combat sport or battle simulation.
@ianbot Рік тому
I'd like to see a self-driving car trained in this way: We just need to use input data of some data of cars driving perfectly (at intersections, changing lanes, parking) and we can make a simulation where an AI agent is given the ability to press the gas pedal, steer left, right, use turn signals, (etc.) and also given input data about the car's position in lane, positions of nearby cars and pedestrians. We already have the technology to gather this data from cameras (tesla). Then we would train the AI agents. And if they can control these soccer players that have at least 20 different joint controls that need such fine tuning, we should be able to train an agent to drive a car, even have races, do tricks, or just drive from point A to B without crashing.
@fruitlukes1736 Рік тому
The red teammate at the top looks like something out of a nightmare 5:55
@abhishtagatya Рік тому
on multi-agent ai, do we have to relearn a strategy for 11 v 11 instead of the current 2 v 2? i assume so because in theory its a different game?
@wurstkatze Рік тому
In the first seconds: "... this Increadible AI..." meanwhile the AI spazzing on the floor xD
@odawgthat3896 Рік тому
Love the videos!!!
@REDSIDEofficial Рік тому
Wow! The first steps of a Simulation World just started, can’t wait to see virtual peoples doing tasks like our own.
@axelwickm Рік тому
The pure PANIC in their running HAHAHAHAHA
@enderyu Рік тому
Don't forget the guy having a mental breakdown at 4:22 and then immediately snapping back to the game
@axelwickm Рік тому
@@enderyu It is all very relatable.
@william_8844 Рік тому
I have always enjoyed your videos and find them way above my head. But I am slowly learning ML. I still can't link what I watch here to what I can do to get there. ... I am looking for projects to work ob
@pearhat640 Рік тому
this channel is so underrated. Also its quite scary
@user-xl7kk1qn2i 9 місяців тому
1:00 the footballers like babies he crying
@TheChipMcDonald Рік тому
They're training them on rotoscoped humans playing, so was the feints with the footwork introducing "noise" that was creating the initial shaking/quivering? When they're running they take lots of tiny steps, which makes me think that's a latent trait of the human data set foot-faking distorting the training?
@sr.railn.m.667 Рік тому
testing 3v3 ir 5v5 matches would be very interesting as well
@calamorta Рік тому
4:22 that's pretty much Messi's signature move.
@ahabkapitany Рік тому
"5 years pass by in 3 days. Are you thinking what I'm thinking?" Well I'm thinking about that Black Mirror episode with a clenched stomach...
@MrJaCraig Рік тому
I love the pretrained red guy in the middle of the pitch. Give him to glow sticks and he looks like he's at a rave.
@hunterjohnson6513 Рік тому
And to think how jaw dropping it was to see open AI dominating a 1v1 against pros in Dota 2 years ago. Unreal how far it’s come and it’s only going to grow exponentially from here
@potts995 Рік тому
1:05 That poor guy in the middle of the field trying so hard to get back up!
@enderyu Рік тому
4:22 The blue guy having a quick panic attack off to the side before returning to the game
@noomade Рік тому
It seems as if introducing some sort of stamina limit will fix a lot of those weird movements. And of course make more stressful body positions use more stamina etc
@paulgaither Рік тому
As a sports fan, it would be great to see 11 on 11 at a larger scale, add the rules of the game, and factor in variables such as height, weight, strength, speed, endurance, etc.
@Walter5850 Рік тому
AI scientists should have a competition to see whose model can train their players better and have an actual virtual football cup.
@tnadymacek Рік тому
Pure gold, they play like half of my classmates on PE :D
@myNamezMe Рік тому
The way they move and play looks so funny and too much training will probably iron out that character.
@andreasmartin9296 Рік тому
The beginning reminds me of Italian soccer players when they play out their drama scenes
@ariseyhun2085 Рік тому
I'm quite curious why many of the graphs have staggers going down, instead of continuously improving. Any idea what that might be about? For example, in "Passing Range" it goes down inthe 1 week range at 6:35
@coder0xff Рік тому
It's complicated because you're working with many variables. Imagine you're going to your friends house but you don't have a map of the roads, just a compass that points to your friends house. You go down a road that gets you closer, but it's a dead end. You have to go back the way you came a little to find the better road that will get you even closer. If we imagine that hip angle is the x axis of a map, and ankle angle is the y axis, then we might settle into an effective ankle angle. But then hey, if we tweak the hip angle a bit we can get even better, but the ankle angle needs to be adjusted again. It's like this, but with way more variables.
@ariseyhun2085 Рік тому
@@coder0xff thank you so much for this explanation!
@Player-ix7rx Рік тому
Ok, now put the code into 22 boston dynamics robots and let's go
@NielsMacLean Рік тому
how powerful of a processing unit did they train for those 5 days of drill training?
@cbob213 Рік тому
So so they make all 4 players (2 on each team) learn from scratch? What happens if they drop an Ai in with a team mate that already knows how to play?? Do they learn faster? What happens if they can learn from a team that is better or worse than them??? Sooo interesting. I’d love to learn how to do more of this stuff. I have a few raspberry pi’s that I’m tinkering with but I bet you need a whole bunch more processing juice to do this type of stuff. I hope one day you can make a video that breaks down how to get into a project from scratch or starting from a GitHub library. What a time to be alive indeed. Just ask SkyNet 😉
@vibovitold Рік тому
"What happens if they drop an Ai in with a team mate that already knows how to play?? Do they learn faster? " in principle they definitely should, because there will be quicker and stronger negative feedback = penalty for incorrect behavior this sort of learning isn't really done by copying or mimicking, but by adjusting the neural network attempting to avoid the penalties
@markaron9356 Рік тому
*DeepMind - Magical Skills, Goals & Assists - 2023 | HD*
@TheBartalamey Рік тому
Watching all this physics simulations and last Boston Dynamics video about Atlas and all the struggles they get, i'm interested when BD will use machine learning instead of direct behavioral coding?
@NigraXXL Рік тому
I'm pretty sure they already do. They have a simulation they use to train stuff, then make adjustments if the output doesn't work in real life
Machine Learning Street Talk
Переглядів 139 тис.
Радіо Свобода
Переглядів 234 тис.
SIGMA PHYSICS ⚛️
Переглядів 28
Andro-news.com
Переглядів 32 тис.
ASMR Detected
Переглядів 51 тис.