COMP 579 Reinforcement Learning
4 credits · Computer Science · Faculty of Science · Offered: Winter
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.
Prerequisites
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.
Prerequisite courses: COMP 551, MATH 222, MATH 223, MATH 323
Plan your whole degree in myDegree. Fit COMP 579 and everything it needs into a plan, term by term. Open myDegree
Source: McGill Course Catalogue. myDegree is an independent student project, not affiliated with McGill University.