Michele Magno

Continual-RL for Generalization in Autonomous Racing on the RoboRacer Platform

This work tries to address the gap in Continual Reinforcement Learning by proposing a continual RL framework based on Continual Backpropagation that is able, with only real-world data, to train a generalistic policy on a set of tracks and then fine- tune it within 15 minutes to outperform classical controllers.