How to Make an Amazing Video Game Bot Easily

In this video, we first go over the history of video game AI, then I introduce OpenAI's Universe, which lets you build a bot that can play thousands of different video games. It has environments for all sorts of games, from Space Invaders, to Grand Theft Auto, to Protein folding simulations. CODING CHALLENGE DUE DATE: Thursday, December 15th. (which is 2 weeks, not 1 week from now like usual) The coding challenge for this video is to make a bot that's better than this video's demo code. Post your Github link in the comments! For your README, just include a 1-3 sentence description of your strategy and instructions on how to run the code.The demo code can be found in the README of the Universe repo. : https://github.com/openai/universe And a Tensorflow based starter bot can be found here: https://github.com/openai/universe-starter-agent Some great learning resources: https://www.nervanasys.com/openai/ http://karpathy.github.io/2016/05/31/rl/ http://kvfrans.com/simple-algoritms-for-solving-cartpole/ https://kofzor.github.io/Reinforcement_Learning_101/ Join other Wizards on our Slack channel: https://wizards.herokuapp.com/ OpenAI asked me to make this video and I gladly said yes. They are awesome!! Please subscribe! And like and comment. That's what keeps me going. And please support me on Patreon: https://www.patreon.com/user?u=3191693 Follow me: Twitter: https://twitter.com/sirajraval Facebook: https://www.facebook.com/sirajology Instagram: https://www.instagram.com/sirajraval/ Instagram: https://www.instagram.com/sirajraval/