Evolving Genetic Neural Network Optimizes Poly Bridge Problems

Evolving Genetic Neural Network Optimizes Poly Bridge Problems

AstroSam

11 месяцев назад

1,060,762 Просмотров

Ссылки и html тэги не поддерживаются


Комментарии:

Ronald Arnyek
Ronald Arnyek - 01.11.2023 03:25

Nice code bullet video

Ответить
Zeke
Zeke - 31.10.2023 20:05

He doesn't have enough time he said.

Ответить
Loli slayer
Loli slayer - 31.10.2023 04:55

This is like a mix of code bullet and real civil engineer😂😂 you got a new sub

Ответить
Aspen
Aspen - 30.10.2023 08:16

So you didnt have the time to do it yourself so you used the time that you DIDNT have to make an ai to do the thing you DIDNT have the time to do

Ответить
MQ
MQ - 28.10.2023 03:37

I know AI doesn't have emotions, but for this survival of the fittest thing it makes sense they would cheat. Sure, you're not going to win, but you'll live.

Ответить
Peter S
Peter S - 25.10.2023 15:45

The reward function ends up being as complex as just solving the problem without AI, lol.

Ответить
Kraik
Kraik - 23.10.2023 05:59

Thank you!
Very interesting.

Ответить
William Duncan
William Duncan - 22.10.2023 21:21

-1 for c#

Ответить
Panagiotis Apostolidis
Panagiotis Apostolidis - 18.10.2023 14:36

a follow up video on this but it minimized stress would be really interesting

Ответить
olli
olli - 15.10.2023 23:47

Your fitness function could have been based on three things: the changes to the road pieces (max distance change, max angle change) and the max distance change of the balls. Also you should have randomized ball size. With keeping the ball as level as possible the main goal. This will help avoid jumps, hills, swings, and dips. If you’re given a straight path of road joints and told to keep it as level as possibly by only adding bridge connections etc.

Ответить
Jhonata Carneiro
Jhonata Carneiro - 29.09.2023 17:30

Astro make your own operating system

Ответить
Сергій Самарук
Сергій Самарук - 27.09.2023 18:03

While watching Matt(@RealCivilEngineerGaming) tweaking his bridges I thought I'd be cool to replace Matt with genetic algorithm. I don't even thing neural network is required for that.
Basically we can give the bridge (with suboptimal but working design) to the computer and ask it to move joints around until it'd land on the cheapest possible bridge without structural modification. That would drastically speed up the search (compared to generating the bridge from scratch) and hopefully show what the design actually is capable of.

And implementing it as a mod/plugin for the original game would be absolutely cool but i have no idea how hard would it be to integrate such thing into the game.

Ответить
Jordan Shackelford
Jordan Shackelford - 11.09.2023 07:13

Are there any games that have AI agents trained like this? I was thinking of adding predator / prey entities into my game and have the predator rewarded by enemies eaten, and the prey rewarded by time survived

Ответить
Alexandre Blais
Alexandre Blais - 29.08.2023 20:23

"I dont have enough time to play the game so il make a new version of it from scratch"

Ответить
Alejandro Estrada
Alejandro Estrada - 28.08.2023 20:29

amazin gg

Ответить
Dan Gingerich
Dan Gingerich - 27.08.2023 18:45

"It isn't the solution we wanted" I instantly thought "It is the solution you deserved." :)

Ответить
TdubMorris
TdubMorris - 26.08.2023 01:56

I would love to see a part 2. Maybe try solving some actual levels with the algorithm and seeing if it would work?

Ответить
CASyHD
CASyHD - 23.08.2023 00:47

So Its not working correctly, its not working for poly bridge and its clickbait. Super cool video bro

Ответить
Mike Collins
Mike Collins - 18.08.2023 21:54

I once heard that an algorithm had been designed to assist in choosing the most efficient route for a road across London. When the program was tested, it came up with an answer in less time than expected - straight down the river.

Ответить