IE 2186 - REINFORCEMENT LEARNING Minimum Credits: 3 Maximum Credits: 3 This is an introductory course on reinforcement learning (RL), a set of techniques used for learning sequential decision making policies from data. The basics of Markov decision processes necessary for RL will be covered, but a firm grasp of undergraduate level probability and basic programming ability (in Python and MATLAB) will be assumed. A wide range of methods (e.g., TD learning, Q-learning, policy gradients) that perform evaluation and control will be covered. The focus in this course will be on applications, implementation, intuition and some theory. Academic Career: Graduate Course Component: Lecture Grade Component: Grad Letter Grade Course Requirements: PREQ: IE 2005 or IE 1070 or Equivalent and IE 1082 PLAN: Industrial Engineering
Click here for class schedule information.
Add to Portfolio(opens a new window)
|