Reinforcement Learning in the Context of Robotics

Months ago, I came across this video of a robot hand rotating a cube (in all 3D) to achieve specific configurations of that cube. This is extremely difficult - the robot has 20 degrees of freedom! This got me interested in the idea of reinforcement learning, a framework that allows the development of agents for a wide variety of problems. Luckily, this coincided with OpenAI releasing the fantastic Spinning Up in Deep RL guide, written by Josh Achiam, a Ph....

February 22, 2019 · Abdul Rahman Dabbour

A Semi-Gentle Introduction to the Kalman Filter

The Kalman Filter, named after Rudolf E. Kálmán - its principle mastermind, was developed around 1960. In short, it is an optimal algorithm used to estimate a state of a linear system by recursively processing data. To illustrate its importance, our professor constantly reminded us that two things got man to the moon: Fortran and the Kalman Filter. To help us understand the algorithm better, let’s take a practical example for the rest of this introduction....

December 22, 2018 · Abdul Rahman Dabbour