Welcome to the fourth and the last week of our course on the Reinforcement Learning for finance. In the last week we saw how the problem of option pricing and hedging can be formulated as Reinforcement Learning model. In this week, we will talk about applications of reinforcement learning for stock trading. We will discuss various problems in quantitative trading that amounts to Reinforcement Learning tasks. We will talk about such problems as optimal portfolio execution, dynamic portfolio management, and index tracking. Then we will develop a simple portfolio model that allows us to address all these problems in the same modeling framework. We will then introduce a Reinforcement Learning approach to such problem, that learns optimal trading or execution policy directly from data, made of states, actions, and rewards. And then, we will discuss an Inverse Reinforcement Learning setting for these problems, where we do not observe rewards, and we will see why it may be more useful than direct Reinforcement Learning setting, in many problems of practical interest. We will then see how Inverse Reinforcement learning works in this setting, and how it can be applied to learn a reward function, also called a utility function, of investor or even of a market. And finally, we will look at the same model but apply it this time to all investors simultaneously, and show how we can use Inverse Reinforcement learning to learn markets-optimal trading strategies. So I hope it's going to be an interesting week. Also please keep in mind that as we already did a few times in the specialization, this week will simultaneously surface an introduction to the last course in this specialization, where we will talk about more involved applications of Reinforcement Learning to problems of finance. So let's start.