Learn Policy Gradients Online

Course outline

This course will cover the following topics:-

(1) Background and definitions

(2) The reward hypothesis

(3) Markov decision process

(4) Reinforcement learning objective

(5) The policy gradient theorem

(6) Reinforcement baseline

(7) State value

(8) Actor critic methods

Prerequisite knowledge

You should have a reasonable background of Machine Learning topics

Learning outcomes

After completing this course you will understand the role of policy gradients as part of reinforcement learning

Software / Hardware requirements

N/A

Q-Learning

2 hours session

Evaluation Feedback

2 hours session

Monte Carlo Methods

1 hours session

Want to upskill or acquire a new skill?

Start Learning!