Mon 14 Sep 2020 04:29:54 PM CST. Page opened.
Join the http://www.discord.com server NTNU https://discord.gg/nWPHsUU. Send a message !register reinforcement-learning to the @NTNU Online Lecturing Support bot
This course focuses on a particular type of unsupervised learning algorithms - reinforcement learning. These algorithms allow a system to learn how to perform tasks (i.e., a sequences of steps to achieve a goal, such as picking up a bottle or winning a game of Go), rather than the more common classification problems discussed in the Machine Learning course. The course covers both standard as well as deep reinforcement learning algorithms.
Your grade in the course depends on the following assessments:
Assignment 1: 20%
Midterm Test: 20%
Assignment 2: 20%
Final Exam: 40%
The course uses the book Reinforcement Learning by Richard S. Sutton and Andrew G. Barto. The second edition is available http://incompleteideas.net/book/the-book-2nd.html.
The course uses a combination of traditional lecture slides and interactive jupyter notebooks. Some of the notebooks are hosted on the Google Colaboratory and Microsoft Azure Notebooks servers.