Explore the concept of Equivariant Reinforcement Learning in this comprehensive lecture by Max Welling from the University of Amsterdam. Delve into the advantages of equivariant approaches, potential gains, and experimental results. Gain insights into Graph Neural Networks and their application in optimization under symmetry. Understand the fundamental principles of Reinforcement Learning and how equivariant methods can enhance its performance. Discover the latest research findings and their implications for the field of machine learning and artificial intelligence.
Overview
Syllabus
Introduction
What is RL
Advantages of Equivariant
Question
Results
Potential gains
Experiments
Graph Neural Networks
Conclusion
Taught by
Simons Institute
Related Courses
-
Harvard CS50’s Artificial Intelligence with Python – Full University Course
4.6 -
Deep Learning Crash Course for Beginners
4.0 -
TensorFlow 2.0 Complete Course - Python Neural Networks for Beginners Tutorial
5.0 -
Equivariant Machine Learning Structured Like Classical Physics
-
Machine Learning with Python
4.6 -
Deep Learning and Neural Networks with Python
