EPISODE · Sep 10, 2018 · 10 MIN
Introduction (Move 37)
from Siraj Raval
Welcome to my new reinforcement learning course titled Move 37! in this 10 week course we'll go over the basics of reinforcement learning up to modern day techniques that involve neural networks called 'deep' reinforcement learning. In this first video, i'll introduce the idea of a Markov Decision Process. This is the basic mathematical framework for framing the reinforcement learning problem. We'll also briefly mention the ideas of a 'policy' and the agent-environment loop. Get hype! Code for this video: https://github.com/llSourcell/Introduction_Move37 Please Subscribe! And like. And comment. That's what keeps me going. The School of AI website is undergoing a site migration right now to handle all the traffic + upgrade the layout. It will be down for the next few hours but check back soon. I promise, you won't miss anything and i'll keep you updated via all my social channels: https://www.theschool.ai Want more education? Connect with me here: Twitter: https://twitter.com/sirajraval Facebook: https://www.facebook.com/sirajology instagram: https://www.instagram.com/sirajraval Github Syllabus: https://github.com/llSourcell/Move_37_Syllabus More learning resources: https://towardsdatascience.com/reinforcement-learning-demystified-markov-decision-processes-part-1-bf00dda41690 https://www.cs.rice.edu/~vardi/dag01/givan1.pdf http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching_files/MDP.pdf https://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-825-techniques-in-artificial-intelligence-sma-5504-fall-2002/lecture-notes/Lecture20FinalPart1.pdf https://artint.info/html/ArtInt_224.html Join us in the Wizards Slack channel: http://wizards.herokuapp.com/ And please support me on Patreon: https://www.patreon.com/user?u=3191693
What this episode covers
Welcome to my new reinforcement learning course titled Move 37! in this 10 week course we'll go over the basics of reinforcement learning up to modern day techniques that involve neural networks called 'deep' reinforcement learning. In this first video, i'll introduce the idea of a Markov Decision Process. This is the basic mathematical framework for framing the reinforcement learning problem. We'll also briefly mention the ideas of a 'policy' and the agent-environment loop. Get hype! Code for this video: https://github.com/llSourcell/Introduction_Move37 Please Subscribe! And like. And comment. That's what keeps me going. The School of AI website is undergoing a site migration right now to handle all the traffic + upgrade the layout. It will be down for the next few hours but check back soon. I promise, you won't miss anything and i'll keep you updated via all my social channels: https://www.theschool.ai Want more education? Connect with me here: Twitter: https://twitter.com/sirajraval Facebook: https://www.facebook.com/sirajology instagram: https://www.instagram.com/sirajraval Github Syllabus: https://github.com/llSourcell/Move_37_Syllabus More learning resources: https://towardsdatascience.com/reinforcement-learning-demystified-markov-decision-processes-part-1-bf00dda41690 https://www.cs.rice.edu/~vardi/dag01/givan1.pdf http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching_files/MDP.pdf https://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-825-techniques-in-artificial-intelligence-sma-5504-fall-2002/lecture-notes/Lecture20FinalPart1.pdf https://artint.info/html/ArtInt_224.html Join us in the Wizards Slack channel: http://wizards.herokuapp.com/ And please support me on Patreon: https://www.patreon.com/user?u=3191693
NOW PLAYING
Introduction (Move 37)
No transcript for this episode yet