Model-Based Reinforcement Learning

In model-based reinforcement learning, an agent uses its experience to construct a representation of the control dynamics of its environment. It can then predict the outcome of its actions and make decisions that maximize its learning and task performance. This tutorial will survey work in this area with an emphasis on recent results. Topics will include: Efficient learning in the PAC-MDP formalism, Bayesian reinforcement learning, models and linear function approximation, recent advances in planning.