Тёмный

AI LEARNS SOCCER 

Sebastian Schuchmann
Подписаться 10 тыс.
Просмотров 13 тыс.
50% 1

Two different artificial neural networks battling each other in a simple game of soccer. I am using Deep Reinforcement Learning to train Neural Networks. Everything shown here is made in Unity3D. The Algorithm used to train this A.I. is called PPO (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/...
The soccer game is included in the ML-Agents Framework, which is provided by Unity on GitHub. For those of you with experience in programming, you can check it out here:
github.com/Unity-Technologies...
Thanks to Unity3D for the awesome framework!
Music by Eric Taylor.

Наука

Опубликовано:

 

21 авг 2019

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 15   
@shivmahabeer9450
@shivmahabeer9450 4 года назад
Have to say I'm loving your videos, bro!
@kylejohnson5595
@kylejohnson5595 4 года назад
Your commentary is cracking me up. Glad I found your channel. Learned about it through an article I read in TNW magazine. You do good work. Thanks for sharing.
@charlieclifton2091
@charlieclifton2091 4 года назад
1:17 top right 🤣
@EmoryM
@EmoryM 4 года назад
When Blue got on top of Red and they just stopped I laughed. Thank you. Next is baseball, I guess?
@samda7109
@samda7109 4 года назад
hi Sebastian, könntest du nicht ein kleines How to machen, in dem du zeigst, wie man einen Agent mit humanoid Rig mittels Deep Learning bei bringen kann sich zu bewegen (gehen, rennen, springen, Drehung links und rechts, evtl. auch rückwärts laufen). Quasi ohne Animationen zu laden. Also einfach nur durch die vorgegebenen Freiheitsgrade des Rig. Und was passiert wenn sich die Umgebung ändert.
@mahraneabid
@mahraneabid 14 дней назад
how to make ai avoid using that back and forth of movement?
@yourcommander3412
@yourcommander3412 4 года назад
lower their suger intake :)
@PickentCode
@PickentCode 5 лет назад
Another great video, keep them coming! Is it possible to teach AI how to play tennis?
@SebastianSchuchmannAI
@SebastianSchuchmannAI 5 лет назад
I will check Tennis out next. It always depends on how much you simplify the game. I will start with a very basic version of Tennis and see how they perform!
@TheUngi
@TheUngi 3 года назад
What are the inputs to the neural network?
@firaswaffle
@firaswaffle 3 года назад
Good
@ONDANOTA
@ONDANOTA 4 года назад
Do martial arts! (i mean striking and damage, not wrestling)
@ONDANOTA
@ONDANOTA 4 года назад
but I guess grappling will emerge anyway as a byproduct of the footwork/positioning
@IgorGabrielan
@IgorGabrielan 4 года назад
soccer.ai
Далее
Unity ML-Agents 1.0 - Training your first A.I
11:55
Просмотров 113 тыс.
AI Learns to Drive a Car! (ML-Agents in Unity)
13:13
Просмотров 73 тыс.
2DROTS vs RISENHAHA! КУБОК ФИФЕРОВ 2 ТУР
11:31
why you were forced to learn the recorder in school
19:34
A.I. in Minecraft
9:20
Просмотров 54 тыс.
AI Learns to Park - Deep Reinforcement Learning
11:05
AI LEARNS BASKETBALL
4:53
Просмотров 11 тыс.
ML-Agents 1.0+ Creating a Mario Kart like AI
16:32
Просмотров 36 тыс.
Neural Network Learns to Play Snake
7:14
Просмотров 4,5 млн
How I created an A.I. that learned to WALK
4:20
Просмотров 10 тыс.
НОВЫЕ ФЕЙК iPHONE 🤯 #iphone
0:37
Просмотров 189 тыс.