Artificial Intelligence: Reinforcement Learning in Python

<div>Ever wondered how AI technologies like OpenAI ChatGPT and GPT-4 really work? In this course, you will learn the foundations of these groundbreaking applications.</div><div><br></div><div>When people talk about artificial intelligence, they usually don’t mean supervised and unsupervised machine learning.</div><div><br></div><div>These tasks are pretty trivial compared to what we think of AIs doing - playing chess and Go, driving cars, and beating video games at a superhuman level.</div><div><br></div><div>Reinforcement learning has recently become popular for doing all of that and more.</div><div><br></div><div>Much like deep learning, a lot of the theory was discovered in the 70s and 80s but it hasn’t been until recently that we’ve been able to observe first hand the amazing results that are possible.</div><div><br></div><div>In 2016 we saw Google’s AlphaGo beat the world Champion in Go.</div><div><br></div><div>We saw AIs playing video games like Doom and Super Mario.</div><div><br></div><div>Self-driving cars have started driving on real roads with other drivers and even carrying passengers (Uber), all without human assistance.</div><div><br></div><div>If that sounds amazing, brace yourself for the future because the law of accelerating returns dictates that this progress is only going to continue to increase exponentially.</div><div><br></div><div>Learning about supervised and unsupervised machine learning is no small feat. To date I have over TWENTY FIVE (25!) courses just on those topics alone.</div><div><br></div><div>And yet reinforcement learning opens up a whole new world. As you’ll learn in this course, the reinforcement learning paradigm is very from both supervised and unsupervised learning.</div><div><br></div><div>It’s led to new and amazing insights both in behavioral psychology and neuroscience. As you’ll learn in this course, there are many analogous processes when it comes to teaching an agent and teaching an animal or even a human. It’s the closest thing we have so far to a true artificial general intelligence.&nbsp; What’s covered in this course?</div><div><ul><li>The multi-armed bandit problem and the explore-exploit dilemma</li><li><span style="font-size: 1rem;">Ways to calculate means and moving averages and their relationship to stochastic gradient descent</span></li><li><span style="font-size: 1rem;">Markov Decision Processes (MDPs)</span></li><li><span style="font-size: 1rem;">Dynamic Programming</span></li><li><span style="font-size: 1rem;">Monte Carlo</span></li><li><span style="font-size: 1rem;">Temporal Difference (TD) Learning (Q-Learning and SARSA)</span></li><li><span style="font-size: 1rem;">Approximation Methods (i.e. how to plug in a deep neural network or other differentiable model into your RL algorithm)</span></li><li><span style="font-size: 1rem;">How to use OpenAI Gym, with zero code changes</span></li><li><span style="font-size: 1rem;">Project: Apply Q-Learning to build a stock trading bot</span></li></ul></div><div><span style="font-size: 1rem;">If you’re ready to take on a brand new challenge, and learn about AI techniques that you’ve never seen before in traditional supervised machine learning, unsupervised machine learning, or even deep learning, then this course is for you.</span></div><div><br></div><div>See you in class!</div><div><br></div><div>"If you can't implement it, you don't understand it"</div><div><ul><li>Or as the great physicist Richard Feynman said: "What I cannot create, I do not understand".</li><li><span style="font-size: 1rem;">My courses are the ONLY courses where you will learn how to implement machine learning algorithms from scratch</span></li><li><span style="font-size: 1rem;">Other courses will teach you how to plug in your data into a library, but do you really need help with 3 lines of code?</span></li><li><span style="font-size: 1rem;">After doing the same thing with 10 datasets, you realize you didn't learn 10 things. You learned 1 thing, and just repeated the same 3 lines of code 10 times...</span></li></ul></div><div><span style="font-size: 1rem;">Suggested Prerequisites:</span></div><div><ul><li>Calculus</li><li><span style="font-size: 1rem;">Probability</span></li><li><span style="font-size: 1rem;">Object-oriented programming</span></li><li><span style="font-size: 1rem;">Python coding: if/else, loops, lists, dicts, sets</span></li><li><span style="font-size: 1rem;">Numpy coding: matrix and vector operations</span></li><li><span style="font-size: 1rem;">Linear regression</span></li><li><span style="font-size: 1rem;">Gradient descent</span></li></ul></div><div><span style="font-size: 1rem;">WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:</span></div><div><ul><li>Check out the lecture "Machine Learning and AI Prerequisite Roadmap" (available in the FAQ of any of my courses, including the free Numpy course)</li></ul></div><div><span style="font-size: 1rem;">UNIQUE FEATURES</span></div><div><ul><li>Every line of code explained in detail - email me any time if you disagree</li><li><span style="font-size: 1rem;">No wasted time "typing" on the keyboard like other courses - let's be honest, nobody can really write code worth learning about in just 20 minutes from scratch</span></li><li><span style="font-size: 1rem;">Not afraid of university-level math - get important details about algorithms that other courses leave out</span></li></ul></div>

What you'll learn:

• Apply gradient-based supervised machine learning methods to reinforcement learning
• Understand reinforcement learning on a technical level
• Understand the relationship between reinforcement learning and psychology
• Implement 17 different reinforcement learning algorithms
• Understand important foundations for OpenAI ChatGPT, GPT-4