Reinforcement learning is an area of machine learning concerned with the behaviour of an agent in an environment, whose goal is to interact with the environment in order to maximize some type of reward. This general idea can be applied to solve a wide range of tasks, from winning at chess to beating the world champion of Go, from teaching a robot how to move to designing new drugs. In this article, we will cover pa…
The Variational Autoencoder (VAE) is a not-so-new-anymore Latent Variable Model (Kingma & Welling, 2014), which by introducing a probabilistic interpretation of autoencoders, allows to not only estimate the variance/uncertainty in the predictions, but also to inject domain knowledge through the use of informative priors, and possibly to make the latent space more interpretable. VAEs can have various applications, mostly related to data generation (for example, image generation, sound gene…