Glen Berseth

I am an assistant professor at the University de Montreal and Mila. My research explores how to use deep learning and reinforcement learning to develop generalist robots.

ReinforcementLeanring Articles


KL Divergence Regularization for RL

Glen B

Intro

Regularization is a very common practice in machine learning. In supervized learning it is used to reduce model complexity. It also helps prevent the model from over fitting the test data. In RL because of the availablility of limitless data regularization does not need to be used to reduce …


Interfacing with Simulators for RL

Glen Berseth

These days, many people want to use one of many new libraries written in python to train deep learning models. In general, python has many powerful and easy to use libraries for performing machine learning. However, many applications that generate data are written in other languages. In particular, many simulators for RL applications are written in C++. Here I will focus on an interface I have found useful for wrapping physics-based simulators in C++.