Friday
Room 1
13:40 - 14:40
(UTC+02)
Talk (60 min)
Building a level 5 autonomous vehicle (in TrackMania)
In games such as chess and go, mankind’s best players have seen themselves beat by machine learning. As the decade came to an end we were also closer than ever before to fully autonomous vehicles, and they are being developed using this very same technology.
In this session we will present to you our self-driving vehicle trained using reinforcement learning. The agent is self-taught, without the use of human input. By using cutting edge technology, we have surpassed the likes of Google and Tesla to solve self-driving vehicles - at least in a video game they didn’t try to solve: TrackMania, a popular racing game. We will present the different parts of our pipeline, ranging from the features that are used to how the car performs actions and the model training itself, which was done using OpenAIs state-of-the-art algorithm called proximal policy optimization. Most importantly, you will get to see the AI in action.
Whether you have prior experience with machine learning or not, we believe you will find the presentation interesting. The talk will contain technical aspects, but they will be presented and explained in a way that makes it possible for beginners and non-technical audience to follow. Perhaps you’re just a curious TrackMania veteran? We will try to make justice to the game you love.
Join us for an hour of fun and entertainment. As a bonus, you might learn something as well!
Manu Gopinathan
Manu is a Senior Developer at Aboveit, a Norwegian consultancy company, and is also in the company management as Team Lead. Being a machine learning enthusiast since he watched The Terminator for the first time, he is also an AI Tech Lead.
With experience from various parts of the stack, Manu is currently part of a team responsible for development and distribution of timetable data for public transportation at Ruter. During his MSc studies at UCSB and the NTNU, he specialized in AI, with his thesis doing an extensive study on gender identification of authors using deep learning and natural language processing.
Day job aside, Manu has held both talks and workshops at several international conferences - he enjoys sharing knowledge. He has also developed an appreciation for the non-technological aspects of a near post-pandemic world, where staring at a wall and saving plants are not considered hobbies anymore.
Malte Loller-Andersen
Malte is a passionate machine learning engineer working for Norkart, operating in the geospatial domain. Through various projects for big Norwegian companies, he has gathered in-depth knowledge about data engineering, machine learning and MLOps.
In addition to diving deep into the technicalities, Malte enjoys sharing knowledge and holding talks at various conferences. Since starting his career he has held workshops and talks at several international conferences, and he will continue doing exactly that until a global pandemic stops him. If a global pandemic even can stop him!