Building a Level 5 Autonomous Vehicle in TrackMania

Explore the development of a self-driving vehicle using reinforcement learning in the popular racing game TrackMania. Dive into the cutting-edge technology behind autonomous vehicles as presenters Manu Gopinathan and Malte Loller-Andersen showcase their AI agent that surpasses major tech companies in this specific gaming environment. Learn about the different components of their pipeline, including feature extraction, action performance, and model training using OpenAI's proximal policy optimization algorithm. Witness the AI in action and gain insights into the technical aspects of machine learning, presented in an accessible manner for both beginners and non-technical audiences. Discover how reinforcement learning techniques used in chess and go are applied to create a fully autonomous vehicle in a virtual racing environment. Enjoy an entertaining and educational hour-long presentation that bridges the gap between advanced AI concepts and the world of gaming.