Join our book community on Discord

https://packt.link/EarlyAccessCommunity

Machine learning is usually classified into three different paradigms: supervised learning, unsupervised learning, and reinforcement learning (RL). Supervised learning requires labeled data and has been the most popularly used machine learning paradigm so far. However, applications based on unsupervised learning, which does not require labels, have been steadily on the rise, especially in the form of generative models.

An RL, on the other hand, is a different branch of machine learning that is considered to be the closest we have reached in terms of emulating how humans learn. It is an area of active research and development and is in its early stages, with some promising results. A prominent example is the famous AlphaGo model, built by Google's DeepMind, that defeated the world's best Go player.

In supervised learning, we usually feed the model with atomic input-output data pairs and hope for the...