CS 598 NJ - Special Topics - Stat Reinforcement Lrng
Subject offerings of new and developing areas of knowledge in computer science intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites. Course Information: May be repeated in the same or separate terms if topics vary.
All class meetings will be online and synchronous. Description: Theory of reinforcement learning, with a focus on sample complexity analyses. The course will provide the necessary background and the mathematical tools for understanding the statistical properties of RL algorithms and the challenges. Specific topics include: (1) MDP basics, (2) finite sample analyses of batch RL (tabular and func approx), (3) state abstractions, (4) importance sampling, (5) PAC exploration (tabular and func approx), (6) Intro to POMDPs and PSRs. Prerequisites: probability and statistics, linear algebra, and basic concepts of machine learning. Some familiarity with Markov chains and numerical analysis are also recommended. For more info, refer to the course website for Fall 2018 (on instructor's homepage). For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister
Option 1Number of Required Visit(s): 0
Course Level: Graduate
Term(s): Fall , Spring