by Kaiser Hamid Rabbi | Released February 2019 | ISBN: 9781789957549

Combine the power of Reinforcement Learning, Deep Learning and Machine Learning to create powerful real-world appsAbout This VideoCombine the power of Reinforcement Learning, Deep Learning, and Machine Learning to create powerful AI for real-world applicationsMaster Facebook's PYTORCH framework, Kivy, and OpenAIGet hands-on experience of Facebook's PYTORCH framework, Kivy and OpenAIGym(Founded by Elon Musk) by creating Artificial Intelligence using Deep Q-Learning and Deep Convolutional Q-LearningThis course is designed with minimal theory and maximal practical implementation (followed by step-by-step instructions) to get you up-and-running.In DetailDo you want to build a virtual self-driving car AI application using the most cutting-edge algorithm of Reinforcement Learning: Deep Q-Learning? Do you want to create an intelligence that can win the famous 90's game—DOOM—by using Deep Convolutional Q-Learning? Deep Q-Learning is the most robust and powerful technique in Artificial Intelligence for solving complex real-world problems. Artificial Intelligence is making our lives easy day by day and reducing human effort everywhere in social media, websites, online stores, and even business. With a less talk and more action approach, this course will lead you through various implementations of Reinforcement Learning techniques by building a virtual self-driving car application and an AI to beat the monsters in DOOM.You may be wondering that why we create artificial intelligence in a game environment. That is because, once we have created our artificial intelligence in a gaming environment with the help of OpenAIGym, we can use those same principles to solve complex real-world problems just by changing and tweaking algorithm parameters. Get your hands on this course to learn the most fascinating technology in the field of Artificial Intelligence and leverage the power of Reinforcement Learning right away!You can find the code for this course on GitHub: https://github.com/PacktPublishing/-Hands-On-Deep-Q-Learning/settings/collaborationDownloading the example code for this course: You can download the example code files for all Packt video courses you have purchased from your account at http://www.PacktPub.com. If you purchased this course elsewhere, you can visit http://www.PacktPub.com/support and register to have the files e-mailed directly to you. Show and hide more

1. Chapter 1 : Getting Started with Reinforcement Learning
   • The Course Overview 00:03:43
   • Artificial Intelligence in a Nutshell 00:04:25
   • Reinforcement Learning Dynamics 00:06:42
   • The Bellman Equation 00:06:31
   • Markov Decision Process 00:05:49
   • Policy versus Plan and Living Penalty 00:08:17
2. Chapter 2 : Fundamentals of Deep Q-Learning
   • Q-Learning Intuition 00:04:40
   • Temporal Difference 00:05:20
   • Learning Phase of Deep Q-Learning 00:02:53
   • Acting Phase of Deep Q-Learning 00:02:33
   • Experience Reply and Action Selection Policies 00:07:29
3. Chapter 3 : Build Self Driving Car with Deep Q-Learning
   • Installing PYTORCH environment 00:04:16
   • Self Driving Car – Part 1 00:01:27
   • Self Driving Car – Part 2 00:04:12
   • Self Driving Car – Part 3 00:08:25
   • Playing with Our SDC AI 00:03:34
4. Chapter 4 : Deep Convolutional Q-Learning Intuition
   • Convolutional Neural Network 00:10:09
   • Deep Convolutional Q-Learning 00:03:03
   • Eligibility Trace 00:04:36
5. Chapter 5 : Create an AI with Deep Convolutional Q-Learning
   • Installing OpenAIGym and ppaquette 00:02:13
   • Build an AI for DOOM – Part 1 00:03:12
   • Build an AI for DOOM – Part 2 00:01:42
   • Build an AI for DOOM – Part 3 00:05:19
   • Playing with our AI in DOOM 00:03:28
Show and hide more