Neural Network Learns to Play Snake using Deep Reinforcement Learning

Can an AI play Snake well by only looking at it? In this video I use two separate deep reinforcement learning algorithms to try to answer that question. The video was heavily inspired by and is a spiritual continuation of CodeBullet's excellent "A.I. Learns to play Snake using Deep Q Learning" (https://www.youtube.com/watch?v=-NJ9frfAWRo)

Twitter: https://twitter.com/safijari Patreon: https://www.patreon.com/jackofsome

SOME OF MY OTHER VIDOES: ○ Snake Programming Stream: https://www.youtube.com/watch?v=NhTT5KWoMZQ ○ Deep RL Stream: https://www.youtube.com/watch?v=psDlXfbe6ok ○ Vanilla Q Learning Stream: https://www.youtube.com/watch?v=psDlXfbe6ok ○ Explaining RL to a baby: https://www.youtube.com/watch?v=GFIKtFSl1XQ ○ 5 Common Python Mistakes: https://www.youtube.com/watch?v=fMRzuwlqfzs ○ Making Python fast: https://www.youtube.com/watch?v=XW32lPcWOxg

VIDEOS MENTIONED: Alex Patrenko's Snake AI: https://www.youtube.com/watch?v=bh_5aIqVTUY OpenAI Hide and Seek: https://www.youtube.com/watch?v=kopoLzvh5jY AlphaGo: https://www.youtube.com/watch?v=8tq1C8spV_g OpenAI Five (Dota): https://www.youtube.com/watch?v=eHipy_j29Xw&t=87s

#deeplearning #machinelearning #ai ... https://www.youtube.com/watch?v=i0Pkgtbh1xw