November 30th15:30, amphi Digiteo (Shannon 660) (see location):
Martin Riedmiller (Google DeepMind)
Title: Deep Reinforcement learning for learning machines
Abstract:Recently, artificial intelligence has experienced a big boost of interest in both academia and even the general public. A lot of this is due to the success of deep learning methods - neural networks with a considerable number of hidden layers, that show amazing results in a variety of domains such as computer vision or speech recognition. In this talk I will in particular focus on data-efficient reinforcement learning methods. I will highlight progress in this area by going through several examples in both simulated and real domains, including soccer robots and Atari playing agents.
Contact: guillaume.charpiat at inria.fr