Reinforcement learning is hot right now! Policy gradients and deep q learning can only get us so far, but what if we used two networks to help train and AI instead of one? Thats the idea behind actor critic algorithms. I'll explain how they work in this video using the 'Doom" shooting game as an example.

Code for this video: https://github.com/llSourcell/actor_critic

i-Nickk's winning code: https://github.com/I-NicKK/Tic-Tac-Toe

Vignesh's runner up code: https://github.com/tj27-vkr/Q-learning-conv-net

Taryn's Twitter: https://twitter.com/tarynsouthern

More learning resources: https://papers.nips.cc/paper/1786-actor-critic-algorithms.pdf http://rll.berkeley.edu/deeprlcourse/f17docs/lecture_5_actor_critic_pdf.pdf http://web.mit.edu/jnt/www/Papers/J094-03-kon-actors.pdf http://mlg.eng.cam.ac.uk/rowan/files/rl/06_actorcritic.pdf http://mi.eng.cam.ac.uk/~mg436/LectureSlides/MLSALT7/L5.pdf

Please Subscribe! And like. And comment. That's what keeps me going.

Want more inspiration & education? Connect with me: Twitter: https://twitter.com/sirajraval Facebook: https://www.facebook.com/sirajology

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: https://www.instagram.com/sirajraval/ Instagram: https://www.instagram.com/sirajraval/