Highly stochastic analytic meta-learning: the Braitenberg vehicles case study

The goal of this project was to investigate meta-learning in reinforcement learning under highly stochastic environments using mathematically tractable and autonomous Braitenberg vehicles. In collaboration with Dr. Mehdi Khamassi (Institut des Systemes Intelligents et de Robotique, CNRS-Universite Pierre et Marie Curie, Paris, France).