Published On Dec 1, 2017
Can we train an AI to complete it's objective in a video game world without needing to build a model of the world before hand? The answer is yes using Q learning! I'll go through several use cases and show some python code of how Q learning works.
Code for this video:
https://github.com/llSourcell/Q_Learn...
Adnan's Winning code:
https://github.com/AdnanZahid/Reinfor...
Alberto's runner up code:
https://github.com/alberduris
Please Subscribe! And like. And comment. That's what keeps me going.
Want more inspiration & education? Connect with me:
Twitter: / sirajraval
Facebook: / sirajology
More learning resources:
http://mnemstudio.org/path-finding-q-...
https://ocw.mit.edu/courses/aeronauti...
http://uhaweb.hartford.edu/compsci/cc...
/ deep-reinforcement-learning-demysitifed-ep...
https://www.cs.cmu.edu/afs/cs/project...
http://cs.stanford.edu/people/karpath...
https://www.quora.com/How-is-policy-i...
http://www0.cs.ucl.ac.uk/staff/d.silv...
Join us in the Wizards Slack channel:
http://wizards.herokuapp.com/
And please support me on Patreon:
https://www.patreon.com/user?u=3191693 Instagram: / sirajraval Instagram: / sirajraval
Signup for my newsletter for exciting updates in the field of AI:
https://goo.gl/FZzJ5w
Hit the Join button above to sign up to become a member of my channel for access to exclusive content! Join my AI community: http://chatgptschool.io/ Sign up for my AI Sports betting Bot, WagerGPT! (500 spots available):
https://www.wagergpt.co