Model-free control and deep learning
Also appears in collection : CEMRACS - Summer school: Numerical methods for stochastic models: control, uncertainty quantification, mean-field / CEMRACS - École d'été : Méthodes numériques pour équations stochastiques : contrôle, incertitude, champ moyen
In this talk I will present some recent developments in model-free reinforcement learning applied to large state spaces, with an emphasis on deep learning and its role in estimating action-value functions. The talk will cover a variety of model-free algorithms, including variations on Q-Learning, and some of the main techniques that make the approach practical. I will illustrate the usefulness of these methods with examples drawn from the Arcade Learning Environment, the popular set of Atari 2600 benchmark domains.