CS 6789

CS 6789

Course information provided by the Courses of Study 2020-2021.

State-of-art intelligent systems often need the ability to make sequential decisions in an unknown, uncertain, possibly hostile environment, by actively interacting with the environment to collect relevant data. Reinforcement Learning is a general framework that can capture the interactive learning setting. This graduate level course focuses on theoretical and algorithmic foundations of Reinforcement Learning. The topics of the course will include: basics of Markov Decision Process (MDP); Sample efficient learning in discrete MDPs; Sample efficient learning in large-scale MDPs; Off-policy policy optimization; Policy gradient methods; Imitation learning & Learning from demonstrations; Contextual Bandits. Throughout the course, we will go over algorithms, prove performance guarantees, and also discuss relevant applications. This is an advanced and theory-heavy course: there is no programming assignment and students are required to work on a theory-focused course project.

When Offered Fall.

Prerequisites/Corequisites Prerequisite: CS 4780, BTRY 3080 or ECON 3130, or MATH 4710, ORIE 3300, MATH 2940. For undergraduates: permission of instructor with minimum grade A in CS 4780.

View Enrollment Information

Enrollment Information
Syllabi: none
  •   Regular Academic Session. 

  • 4 Credits Stdnt Opt

  • 18402CS 6789  LEC 001

    • TROnline Meeting
    • Sep 2 - Dec 16, 2020
    • Sun, W

  • Instruction Mode: Online
    Enrollment limited to CIS PhD and CS MS students only.

Enrollment Information
Syllabi: none
  •   Regular Academic Session. 

  • 4 Credits Stdnt Opt

  • 18572CS 6789  LEC 030

  • Instruction Mode: Online
    Taught in NYC at Cornell Tech. Enrollment limited to Cornell Tech PhD students. Streamed from Ithaca to Cornell Tech.