香蕉视频

McGill.ca / Vue d'ensemble / Summer Studies / Summer 2021 Courses

Derni猫res mises 脿 jour en lien avec la COVID-19 disponibles ici.
Latest information about COVID-19 available here.

COMP 579 Reinforcement Learning (4 unit茅s)

Nota : Ceci est la version 2020鈥�2021 de l'annuaire 茅lectronique. Veuillez mettre 脿 jour l'ann茅e dans la barre d'adresse de votre navigateur pour une version plus r茅cente de cette page, ou .

Offered by: Informatique (Sciences)

Vue d'ensemble

Informatique (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: This course is not scheduled for the 2020-2021 academic year.

Instructors: There are no professors associated with this course for the 2020-2021 academic year.

  • 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