EPISODE · Dec 9, 2017 · 9 MIN
Solving the Basic Game of Pong
from Siraj Raval
Building an AI to beat pong using just the pixels of the screen as input with no hard-coded rules? Yes, its possible. We'll solve this using an approach called "Policy Gradients" which is even more popular than Q-learning. I'll show you how its done using a mix of animations, code, and theory. Let's beat pong! Code (and challenge) for this week: https://github.com/llSourcell/policy_gradients_pong Alex's Winning code: https://github.com/msoedov/q-learner Aditya's Runner up code: https://github.com/avp1598/q_learning 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 More learning resources: http://karpathy.github.io/2016/05/31/rl/ https://medium.com/@awjuliani/super-simple-reinforcement-learning-tutorial-part-2-ded33892c724 http://minpy.readthedocs.io/en/latest/tutorial/rl_policy_gradient_tutorial/rl_policy_gradient.html http://pemami4911.github.io/blog/2016/08/21/ddpg-rl.html http://kvfrans.com/simple-algoritms-for-solving-cartpole/ https://theneuralperspective.com/2016/11/25/reinforcement-learning-rl-policy-gradients-i/ 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/
What this episode covers
Building an AI to beat pong using just the pixels of the screen as input with no hard-coded rules? Yes, its possible. We'll solve this using an approach called "Policy Gradients" which is even more popular than Q-learning. I'll show you how its done using a mix of animations, code, and theory. Let's beat pong! Code (and challenge) for this week: https://github.com/llSourcell/policy_gradients_pong Alex's Winning code: https://github.com/msoedov/q-learner Aditya's Runner up code: https://github.com/avp1598/q_learning 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 More learning resources: http://karpathy.github.io/2016/05/31/rl/ https://medium.com/@awjuliani/super-simple-reinforcement-learning-tutorial-part-2-ded33892c724 http://minpy.readthedocs.io/en/latest/tutorial/rl_policy_gradient_tutorial/rl_policy_gradient.html http://pemami4911.github.io/blog/2016/08/21/ddpg-rl.html http://kvfrans.com/simple-algoritms-for-solving-cartpole/ https://theneuralperspective.com/2016/11/25/reinforcement-learning-rl-policy-gradients-i/ 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/
NOW PLAYING
Solving the Basic Game of Pong
No transcript for this episode yet