Introduction to Policy Based Methods for Reinforcement Learning

Start Course
level
Advanced
Subject
Machine Learning
Course Length
1:02:23
Subscription
Data Academy

Course Description

This course looks at policy based methods of reinforcement learning, principally the drawbacks to value based methods like Q learning that motivate the use of policy gradients. This is part of the Reinforcement Learning Workshop learning path. Complete this path to learn how to use reinforcement learning in a variety of ML and AI problems.

Requirements

  • As part of the Reinforcement Learning Workshop path, you will know Python as well as have knowledge of basic AI and machine learning principles, as well as the basics of reinforcement learning. You will also be able to use TensorFlow 2 and OpenAI Gym, and have an understanding of Monte Carlo methods.