EPISODE · Aug 13, 2018 · 13 MIN
OpenAI Five vs Dota 2 Explained
from Siraj Raval
How did OpenAI's team of 5 neural networks manage to beat some of the world's best DOTA 2 players? Also, why would OpenAI dedicate so much time and energy to defeating video game players? In this video, I'll explain in detail the cutting edge research techniques OpenAI used to create such an incredible AI algorithm, and how it could be used in the real world. These techniques include Long Short Term Memory Recurrent Neural Networks, Proximal Policy Optimization, and a custom rollout system they've dubbed 'Rapid'. Code for this video: https://github.com/llSourcell/OpenAI_Five_vs_Dota2_Explained Please Subscribe! And like. And comment. That's what keeps me going. Want more education? Connect with me here: Twitter: https://twitter.com/sirajraval instagram: https://www.instagram.com/sirajraval Facebook: https://www.facebook.com/sirajology This video is apart of my Machine Learning Journey course: https://github.com/llSourcell/Machine_Learning_Journey More Learning Resources: https://blog.openai.com/openai-five/ https://towardsdatascience.com/the-science-behind-openai-five-that-just-produced-one-of-the-greatest-breakthrough-in-the-history-b045bcdc2b69 https://blog.openai.com/openai-baselines-ppo/ http://colah.github.io/posts/2015-08-Understanding-LSTMs/ https://www.youtube.com/watch?v=i_McNBDP9Qs&vl=en Join us in the Wizards Slack channel: http://wizards.herokuapp.com/ Sign up for the next course at The School of AI: https://www.theschool.ai And please support me on Patreon: https://www.patreon.com/user?u=3191693 #SirajRaval #OpenAI #Dota2
What this episode covers
How did OpenAI's team of 5 neural networks manage to beat some of the world's best DOTA 2 players? Also, why would OpenAI dedicate so much time and energy to defeating video game players? In this video, I'll explain in detail the cutting edge research techniques OpenAI used to create such an incredible AI algorithm, and how it could be used in the real world. These techniques include Long Short Term Memory Recurrent Neural Networks, Proximal Policy Optimization, and a custom rollout system they've dubbed 'Rapid'. Code for this video: https://github.com/llSourcell/OpenAI_Five_vs_Dota2_Explained Please Subscribe! And like. And comment. That's what keeps me going. Want more education? Connect with me here: Twitter: https://twitter.com/sirajraval instagram: https://www.instagram.com/sirajraval Facebook: https://www.facebook.com/sirajology This video is apart of my Machine Learning Journey course: https://github.com/llSourcell/Machine_Learning_Journey More Learning Resources: https://blog.openai.com/openai-five/ https://towardsdatascience.com/the-science-behind-openai-five-that-just-produced-one-of-the-greatest-breakthrough-in-the-history-b045bcdc2b69 https://blog.openai.com/openai-baselines-ppo/ http://colah.github.io/posts/2015-08-Understanding-LSTMs/ https://www.youtube.com/watch?v=i_McNBDP9Qs&vl=en Join us in the Wizards Slack channel: http://wizards.herokuapp.com/ Sign up for the next course at The School of AI: https://www.theschool.ai And please support me on Patreon: https://www.patreon.com/user?u=3191693 #SirajRaval #OpenAI #Dota2
NOW PLAYING
OpenAI Five vs Dota 2 Explained
No transcript for this episode yet