Course curriculum

    1. Overview

    2. Prerequisites

    3. Reinforcement Learning

    4. Three spaces

    5. Observation space

    6. Action space

    7. Markov Decision Process (MDP)

    8. MDP explained

    9. MDP state

    10. Reward for action

    11. MDP state example

    12. State space

    13. State after an action

    14. Maximise reward

    15. Summary

    1. Recap

    2. MDP Recap continued

    3. Possible states

    4. An example

    5. Reward based actions

    6. Determine if the action is good

    7. Reward Notation

    8. Probability of Decision

    9. Probability Notation

    10. Formal definition

    11. MDP defined

    12. Why MDP

    13. Policy

    14. Policy example

    15. Need for Policy

    16. How to build Policy

    1. Recap

    2. Goodness of a state

    3. Find value of state

    4. Actions we can take

    5. States an action lead to

    6. How good a state is

    7. Repeat for every state

    8. Math Notation

    9. Determine good action

    10. More Specific Math Notation

    11. Include Gamma

    12. Congratulations on completing this course!

About this course

  • $295.00
  • 43 lessons
  • 2 hours of video content

What others are saying about this course

5 star rating

Review of Reinforcement Learning & MDP

Stanley Wang

The instructor was well spoken as always, made his points clear, and had materials prepped so there were no delays in the material being delivered. I wish so...

Read More

The instructor was well spoken as always, made his points clear, and had materials prepped so there were no delays in the material being delivered. I wish some illustrations and the final equation at the end were a bit clearer.

Read Less
5 star rating

Clear tone of addressing Reinforcement Learning

Aidan Chan

It would be more beneficial if there was a real life example in the introduction that could directly relates to this topic, and how does AI learn based on th...

Read More

It would be more beneficial if there was a real life example in the introduction that could directly relates to this topic, and how does AI learn based on the same principles. It will be fun if there is higher emphasis on why there would be a policy framework formed

Read Less
5 star rating

very good

Thurston Bandala

Read Less