Hands on introduction to reinforcement learning in Python

One of the biggest barriers to traditional machine learning is that most supervised and unsupervised machine learning algorithms need huge amounts of data to be useful in real world use cases. Even then, the AI is unable to learn as it goes without human supervision and feedback. What if an AI could learn from scratch? As one of the most famous examples, Google's DeepMind built AlphaGo, which was able to beat the best Go player in history, Lee Sedol. To learn optimal strategies, it used a combination of deep learning and reinforcement learning -- as in, by playing hundreds of thousands of Go games against itself.