# NVIDIA’s New AI Trained For 10 Years! But How? 🤺

## Метаданные

- **Канал:** Two Minute Papers
- **YouTube:** https://www.youtube.com/watch?v=1kV-rZZw50Q
- **Дата:** 19.07.2022
- **Длительность:** 8:06
- **Просмотры:** 1,345,808
- **Источник:** https://ekstraktznaniy.ru/video/13513

## Описание

❤️ Check out Weights & Biases and sign up for a free demo here: https://wandb.com/papers 
❤️ Their mentioned post is available here (thank you Soumik!): http://wandb.me/ASE

📝 The paper "ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters" is available here:
https://nv-tlabs.github.io/ASE/

📝 Our material synthesis paper with the latent space is available here:
https://users.cg.tuwien.ac.at/zsolnai/gfx/gaussian-material-synthesis/

❤️ Watch these videos in early access on our Patreon page or join us here on YouTube: 
- https://www.patreon.com/TwoMinutePapers
- https://www.youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg/join

🙏 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, Eric Martel, Geronimo Moralez, Gordon Child, Ivo Galic, Jace O'Brien, Jack Lukic, John Le, Jonas, Jonathan, Kenneth Davi

## Транскрипт

### 10 Years of training? []

dear fellow Scholars this is two minute papers with Dr car today you will see an absolute Banger paper this is about how amazingly nvidia's virtual characters can move around after they have trained for 10 years we don't have 10 years for a project well luckily we don't have to wait for 10 years why is that I will tell you exactly why in a moment but believe me these folks are not Natural Born Warriors they are AI agents that have to train for a long time to become so good so how does that work well first our candidates are

### After 1 week [0:42]

fed a bunch of basic motions and then are dropped into Nvidia Isaac which is a virtual gym where they can hone their skills but unfortunately they have none after a week of training I expected the that they would showcase some amazingly athletic Warrior moves but instead we got this oh my goodness well let's be optimistic and say that they are practicing Judo where the first lesson is learning how to fall yes let's say that then after 2 months oh we can

### After 4 months [1:23]

witness some improvement well now they are not falling and they can do some basic movement but they still look like

### After 2 years [1:31]

constipated Warriors after 2 years we are starting to see something that resembles true fight moves these are not there yet but they have improved a great deal except this chap goes like sir I've been training for two years I've had enough and now I shall leave in style I wonder what these will

### After 10 years! [1:55]

look like in eight more years of training well hold on to your papers and let's see together oh my that is absolutely amazing now that's what I call a bunch of real Fighters see time is the answer it even made our stylish chap take his training seriously so which one is your favorite from here did you find some interesting movements let me know in the comments below now I

### How did they train for 10 years? [2:25]

promise that we will talk about the 10e thing so did scientists at Nvidia start this paper in 2012 well not quite this is 10 years of training but in a virtual world however a real world computer simulates this virtual world and it can do it much quicker than that how much quicker well a powerful machine can simulate these 10 years not in 10 years but in 10 days oh yeah yes now that

### 1. Latent spaces [3:01]

sounds much better and we are not done yet not even close when reading this paper I was so happy to find out that this new technique also has four more amazing features one it works with latent spaces what is that a latent space is a made up place where similar kinds of data are laid out to be close to each other in our earlier paper we used such a space to create beautiful virtual materials for Virtual Worlds Nvidia here uses a latent space to switch between the motion types that the character now knows and not only that but their AI also learned how to weave these motions together even if they were not combined together in the training data that is incredible two this is my

### 2. Robust recovery [3:52]

favorite it has to be they not only learn to fall but in those 10 years they also had plenty of opportunity to learn to get up do you know what this means of course this means the favorite pastime of the computer Graphics researcher and that is throwing boxes at virtual characters we like to say that we are testing whether the character can recover from random perturbations that sounds a little more scientific and these AI agents are passing with flying colors or flying boxes if you will wow three

### 3. The controls are 👌 [4:35]

also the controls are excellent look this really has some amazing potential to be used in Virtual Worlds because we can even have the character face one way and move into a different direction at the same time more detailed poses can also be specified and what's more with this we can even enter a virtual environment and strike down these evil

### 4. Adversaries [5:01]

pillars with Precision loving it for these motions are synthesized adversarially this means that we have a generator neural network creating these new kinds of motions but we connect it to another neural network called the discriminator that watches it and ensures that the generated motions are similar to the ones in the data set and seem real too and as they SLE each other they also improve together and in the end we take only the motion types that are good enough to fool the discriminator hopefully these human eye too and as you see the results speak for themselves if we wouldn't be doing it this way here is what we would get if we train these Agents from scratch and yes while we are talking about training this did not

### A great life lesson [5:57]

start out well at all imagine if scientists at Nvidia quit after just one week of training which is about 30 minutes in real time these results are not too promising are they but they still kept going and the result was this

### The Third Law of Papers [6:15]

that is excellent life advice right there and also an excellent opportunity for us to invoke the Third Law of papers not the first the third one this says that a bad research fails 100% of the time while a good one only fails 99% of the time hence what you see here is always just 1% of the work that was done and all this is done by Nvidia so I am sure that we will see this deployed in real world projects where these amazing agents will get democratized by putting it into the hands of all of us what a time to be alive so that's the get your mind going what would you use this for let me know in the comments below what you see here is a report of this exact paper we have talked about which was made by weights and biases I put a link to it in the description make sure to have a look I think it helps you understand this paper better weights and biases provides tools to track your experiments in your deep learning projects using their system you can create beautiful reports like this one to explain your findings to your colleagues better it is used by many prestigious Labs including open AI Toyota research GitHub and more and the best part is that weights and biases is free for all individuals academics and open-source projects make sure to visit them through wb. com papers or just click the link in the video description and you can get a free demo today our thanks to weights and biases for their long-standing support and for helping us make better videos for you thanks for watching and for your generous support and I'll see you next time