Skip to content

Latest commit

 

History

History

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Chapter 02: Markov Decision Processes and Bellman Equations

In this Chapter you will learn more in details about MDPs and Bellman Equations.

Examples

Examples of this chapter are:

In this example you will practice with MDPs, you will learn how to calculate the value function for a given policy and how to calculate the action value function.

Exercises

Here you can find all exercises of this chapter:

  • Bellman Equation for MRPs: link
  • Solving MDPs: Linear Programming: link

In these exercises you will practice with Markov Reward Processes (MRPs) and with the Linear Programming solution of Markov Decision Processes.

Activity

The activity of this chapter is:

In this activity you will learn how to formalize a classic RL environment (Gridworld) composed of good states and bad states. The objective is to solve the environment finding the state-value function for all states using Bellman Equations.