Sounds like it would be a lot of fun to code. I don't know if something similar has been done before. You going to make a project thread if you do it?
|
Thinking of building a neural network to train an npc based on how players interact with it... anyone done anything like this yet?
Yes I will post updates and images/videos on how the npc interacts. I'm currently just setting my AWS enviroment up, I'm currently using elvarg v3.1 as my base since I have decided to start building a server again.
Will just be fixing up any bugs that I find, converting into a microservice architecture... will be storing all data off the instances and probably S3 or a mongo... rebuild portions of the base to be more reactive. Might just start using RxJava or Reactive Streams libraries to do that
The reason I'm doing it is because I'm actually testing my skills at building enviroments in AWS, I'm writing my AWS developer cert soon and need to be ready for anything. I'm also building this so that I can make a high performance, scaleable, robust enviroment to show my skills to other company's in my area. So using this as a stepping stone to further my experience.
In ArteroPk they did something similar but with an account not an npc.. They called it Artero Bot or something.
The bot would pickup text messages sent near it for stuff like "Pc whip" and he would reply with the already setup response to that.
Staff members could add replies and whatnot through ingame commands and even mute/ban/jail members by mentioning it before hand.
Like for example: Artero bot, ban Ubernation 99 hours
The account would then be banned.
« Previous Thread | Next Thread » |
Thread Information |
Users Browsing this ThreadThere are currently 1 users browsing this thread. (0 members and 1 guests) |