91滴滴

Updated: Sun, 10/06/2024 - 10:30

From Saturday, Oct. 5 through Monday, Oct. 7, the Downtown and Macdonald Campuses will be open only to 91滴滴 students, employees and essential visitors. Many classes will be held online. Remote work required where possible. See Campus Public Safety website for details.

Du samedi 5 octobre au lundi 7 octobre, le campus du centre-ville et le campus Macdonald ne seront accessibles qu鈥檃ux 茅tudiants et aux membres du personnel de l鈥橴niversit茅 91滴滴, ainsi qu鈥檃ux visiteurs essentiels. De nombreux cours auront lieu en ligne. Le personnel devra travailler 脿 distance, si possible. Voir le site Web de la Direction de la protection et de la pr茅vention pour plus de d茅tails.

Minerva Class Scheduling Visit for course dates & times.

91滴滴.ca / Overview / All Courses
important

Note: This is the 2022鈥�2023 eCalendar. Update the year in your browser's URL bar for the most recent version of this page, or .

COMP 579 Reinforcement Learning (4 credits)

Offered by: Computer Science (Faculty of Science)

Overview

Computer Science (Sci) : Bandit algorithms, finite Markov decision processes, dynamic programming, Monte-Carlo Methods, temporal-difference learning, bootstrapping, planning, approximation methods, on versus off policy learning, policy gradient methods temporal abstraction and inverse reinforcement learning.

Terms: Winter 2023

Instructors: Precup, Doina (Winter)

  • Prerequisite: A university level course in machine learning such as COMP 451 or COMP 551. Background in calculus, linear algebra, probability at the level of MATH 222, MATH 223, MATH 323, respectively.

Back to top