Workshop / Overview

This half-day tutorial addresses the emergence of machine learning techniques, specifically reinforcement learning, within the classic control domain for both image-based and non-image based applications. Segway-like platforms and autonomous driving scenarios serve as illustrative models, providing detailed background for deeper understanding of learning-based control approaches.

For the latest on the tutorial's schedule, setup hints, and frequent Q/A, Kindly read the tutorial's web page on:

The hands-on component starts with a code walk-through, to modify and experiment with simulator-based learning algorithms. Subsequently, the simulator-trained models are then deployed on 1:10 scale rovers for testing and evaluation. Furthermore, selected topics such as performance metrics, generalization, and architectural design/debugging concepts will be covered as time allows.

Participants are encouraged to form 2-4 person groups for an end of session competition.

Workshop / Outcome

Participants will be able to acquire sufficient understanding of the machine learning role within the presented classic control frameworks, and the associated real-world scenarios.

Workshop / Difficulty

Intermediate level

Workshop / Prerequisites

  • Fundamentals of Python
  • Fundamentals of PyTorch
  • Fundamentals of machine learning and/or control theory.
  • A notebook with installed Python, PyTorch, and Gym.

Track / Co-organizers

Adam Barclay

Researcher, v12-labs

Alexandra Tiska

Creative Designer, w12-Labs

AMLD EPFL 2020 / Workshops

A Conceptual Introduction to Reinforcement Learning

With Kevin Smeyers, Katrien Van Meulder & Bram Vandendriessche

09:00-12:30 January 251ABC

Applied Machine Learning with R

With Dirk Wulff, Markus Steiner & Michael Schulte-Mecklenbeck

09:00-17:00 January 25Foyer 6

Augmenting the Web browsing experience using machine learning

With Oleksandr Paraska, Vasily Kuznetsov, Tudor Avram & Levan Tsinadze

09:00-12:30 January 253A

AMLD / Global partners