profile-image

Matej Zečević

Compressing Linear Programs

Linear Programs describe the mathematical formulations of an optimization problem in which a quantity of interest is being chosen in such way that an objective...

$$\begin{equation*} [A]:=\Pi_{\mathcal{P}_{\infty}}^{S} A \Pi_{\mathcal{Q}_{\infty}} \end{equation*}$$

Moment 37: Daigo Umehara in a Flow State

Competitive Gaming has gained momentum over the past years, making the events bigger and more wide spread. The Evolution Championship Series has been considered to...

Placeholder-Image Representative Image of the Post

Model-Free Reinforcement Learning

Reinforcement Learning (RL) is concerned with the problem of an agent trying to maximize a scalar reward signal through interaction within its environment [1]. During...

$$\begin{equation*} \label{eq:2}g = \mathbb{E}\left[ \sum_{t=0}^{\infty} \phi_t \nabla_{\pmb{\theta}} \log \pi_{\pmb{\theta}}(\bf{a}_t \mid \bf{s}_t) \right]\end{equation*}$$

On Why Causality is Needed

“All the impressive achievements of deep learning amount to just curve fitting,” is a public statement attributed to Turing award winner Judea Pearl. Arguably this...

Placeholder-Image Representative Image of the Post

An Example for a Personal Cloud System

A personal cloud can be useful for several reasons. Common arguments involve topics within privacy, cost and personal growth. That is, when hosting your own...

Placeholder-Image Representative Image of the Post