AI Learns to Escape 1 LIFE Lvl's using Reinforcement Learning

AI Teaches Itself How to Escape!
In this video an AI named Conor learns how to escape 6 rooms I've designed.
The AI was trained using Deep Reinforcement Learning, a method of Machine Learning which involves rewarding the agent for doing something correctly, and punishing it for doing anything incorrectly.
Conor's actions are controlled by a Neural Network that's updated after each attempt in order to try to give Conor more rewards and less punishments over time.
Everything in this video (except for the music) was created entirely by myself using Unreal Engine 5.
#artificalintelligence #neuralnetwork #evolution
Current Subscribers: 134
#ai #neuralnetwork #ailearning

[@w1szpYT]

I’m proud to be your 184th subscriber 😊

[@Drakoman07]

What's the program used to run these simulations? I see multiple channels doing similar things, and they all have this same visual theme.

[@liamtilliam5866]

I love this, you're extremely underrated.

[@bilalessabbar7132]

The fact you're that supportive when the AI does stupid moves makes it even better

[@pcv55]

Good video

[@squirrelaa]

Albert but fancier

[@patolinoD4]

Very good, congratulations on the video. I created a very similar one, but simpler and I’m having a lot of difficulty correcting the reward parameters, punishment and especially the ml-agents configuration parameters. I’d love to know if you could help me with this? I will be happy to pay for your service if you need it.

[@patolinoD4]

I’ve been stuck in this problem for almost 1 month, I tried to ask for help from several similar channels and everyone ignored me. Please help me

[@patolinoD4]

I tried to contact Albert from AIWarehouse and without success lol

[@ti9502]

Hello, What is the name of this game?

[@lottiemorris7618]

Could you make one where the ai has to do battle with other ai

[@problyNotJava]

the captions suck