MP4 | Video: AVC 1280x720 | Audio: AAC 44KHz 2ch | Duration: 1 Hour | 428 MB
Genre: eLearning | Language: English
In March 2016, the Google DeepMind program called AlphaGo, beat eighteen-time world champion Lee Sedol in a five-game Go match. Reinforcement learning was integral to AlphaGo's win. In this course, you'll delve into the fascinating world of reinforcement learning to see how this machine learning approach actually works. You'll learn what reinforcement learning is, how it's used to optimize decision making over time, and how it solves problems in games, advertising, and stock trading. The course covers theory and practice, and provides a detailed example, where you'll use reinforcement learning to create an optimized S&P 500 stock trading strategy. This is an intermediate level course requiring Python knowledge and previous experience in machine learning with both the supervised learning and unsupervised learning methods. Before starting the course, learners should have Python 3.5 (or higher) installed, a text editor, and access to Git.
Explore the basic concepts behind reinforcement learning
See how reinforcement learning applies to problems in games and stock trading
Learn about optimizing for the short, medium, and long term using Bellman equations
Understand value iteration and the Markov decision processes
Gain hands-on experience by building an optimal stock trading strategy using Q-learning