The RL Probabilist Adventures in RL, ML, and probability

KL Divergence for Machine Learning

A writeup introducing KL divergence in the context of machine learning, various properties, and an interpretation of reinforcement learning and machine learning as minimizing KL divergence Read more

Control as Inference

Reinforcement learning is traditionally inspired by maximizing reward. This article presents the interpretation of reinforcement as doing inference in a probabilistic graphical model, as introduced in the control-as-inference literature. Read more

Quick ML

A simple and clean presentation of code for nearest neighbors, linear regression, and logistic regression. We've carefully written the code to make it as close to pseudocode as possible. Read more

TensorFlow: A Beginner's Guide

In this article, we familiarize the reader with the basics of Tensorflow by constructing various machine learning models from linear regression to convolutional neural networks. Read more