Тёмный

AI FIGHT WITH CARS 

Sebastian Schuchmann
Подписаться 10 тыс.
Просмотров 6 тыс.
50% 1

Neural Network controlled Cars are fighting. This game was programmed using Unity3D with Reinforcement Learning (Machine Learning) using the ML-Agents Framework. The Algorithm used to train this A.I. is called PPO and it was developed by OpenAI. My name is Sebastian Schuchmann from Germany and I hope you enjoyed this video.
If you want to support me! :)
Patreon: www.patreon.com/user?u=25285137
Twitter: / sebastianschuc7
If you want to get in contact with me, go to my Webform :)
www.sebastian-schuchmann.com/...

Наука

Опубликовано:

 

3 окт 2019

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 20   
@opokusm
@opokusm 4 года назад
Nice video, you could probably avoid cars going in circles by randomizing their positions at the start, otherwise each car learns to constantly compensate for opponent pushing them at one direction.
@Timotheeee1
@Timotheeee1 3 года назад
when I made an ai that can park a truck it also had a tendency to spin in circles
@joshuamanasye
@joshuamanasye 4 года назад
YESS!! I WANNA SEE MORE! But keep all the funny ai fails part too while learning
@akulvohra5344
@akulvohra5344 4 года назад
This is surprisingly high quality production, keep it up!
@SebastianSchuchmannAI
@SebastianSchuchmannAI 4 года назад
Thanks! Cool to hear, I try my best
@eL3ctric
@eL3ctric 4 года назад
would youd mind sharing some od the behind the scenes?
@SebastianSchuchmannAI
@SebastianSchuchmannAI 4 года назад
Yeah for sure. I try to keep the technical stuff to a minimum in the videos. This whole thing runs in a 3D game engine called Unity3D. It is really powerful. The Unity guys have a Machine Learning Framework called ML-Agents, which I use for most of my stuff. It implements algorithms like PPO (this is the same stuff OpenAI uses). I am currently in the process of moving more of my training over in the cloud to speed up the production time.. but of course this comes at a cost. Hope that answers some of your questions! :)
@aigen-journey
@aigen-journey 4 года назад
@@SebastianSchuchmannAI That wasn't really too specific :) What's the reward structure and how did you set-up those asymmetric agents?
@mohammedthousifshaik3628
@mohammedthousifshaik3628 4 года назад
just wow!
@tylerk3130
@tylerk3130 4 года назад
Congratulations, your AI invented the PIT maneuver without knowing wtf that is. Very cool, easy choice to sub. I love the simplistic art style of your worlds. Are you open sourcing the environments? I'm not much of an RL guy myself, but I would love to see someone come up with a demolition derby type multi agent game where each player has different motivations.
@SebastianSchuchmannAI
@SebastianSchuchmannAI 4 года назад
In General I am a big fan of open sourcing my environments but some of the assets like the cars are bought so it is not possible in this case
@tylerk3130
@tylerk3130 4 года назад
@@SebastianSchuchmannAI Ah, that's a real shame, but understandable. Looking forward to more great RL content :)
@Adama_Now
@Adama_Now 4 года назад
very cool! I wish I knew how to do something like this.
@SebastianSchuchmannAI
@SebastianSchuchmannAI 4 года назад
You can learn it, no problemo 😄
@philhiett5027
@philhiett5027 4 года назад
Great AI videos..... but I wish you wouldn't drop a lone F-Bomb in each one... it makes it hard to show these to my students!
@SebastianSchuchmannAI
@SebastianSchuchmannAI 4 года назад
Good to know. I'll try to remember for the next one :)
@robosergTV
@robosergTV 4 года назад
Did you use just two brains? I found from my tests that without a league like what Deepmind did for Alphastar if you train just two agents in a competitive setting they will perpetually invent new strategies and forget the old ones.
@SebastianSchuchmannAI
@SebastianSchuchmannAI 4 года назад
Yes, two brains. I really don't think my results are great and they would probably forget the old ones, too. How did you manage to create League setting? Did you just create your own?
@michelcusteau3184
@michelcusteau3184 4 года назад
Hey, very cool videos. What do you use to perform all these simulations?
@SebastianSchuchmannAI
@SebastianSchuchmannAI 4 года назад
Unity3D :)
Далее
A.I. in Minecraft
9:20
Просмотров 54 тыс.
ML-Agents 1.0+ Creating a Mario Kart like AI
16:32
Просмотров 36 тыс.
AI LEARNS TENNIS
4:33
Просмотров 5 тыс.
Why GPT-3 changes everything (and how it works)
13:09
Unity ML-Agents - Under the Hood (How it works)
5:47
Unity ML-Agents 1.0+  - Self Play explained
12:46
Просмотров 10 тыс.
Codex, the model that has learned to code
8:47
Просмотров 4,3 тыс.
Телефон-електрошокер
0:43
Просмотров 1,3 млн
$1 vs $100,000 Slow Motion Camera!
0:44
Просмотров 27 млн
ЗАБЫТЫЙ IPHONE 😳
0:31
Просмотров 17 тыс.
Красиво, но телефон жаль
0:32
Просмотров 1,5 млн