Explore inverse reinforcement learning in this 38-minute lecture from Pascal Poupart's CS885 course at the University of Waterloo. Delve into topics such as supervised learning, combat applications, feature matching, maximizing margins, and optimization problems. Learn about nonlinear rewards, policy induction, and witness a practical demonstration. Access accompanying slides on the course website for enhanced understanding of this advanced machine learning concept.
Overview
Syllabus
Intro
Supervised Learning
Inverse RL
Combat Applications
General Approach
Feature Matching
Feature Expectations
Maximizing the Margin
Optimization Problem
Future Expectations
Implementation
Nonlinear Reward
Inducing a Policy
Demo
Taught by
Pascal Poupart
