Explore policy gradient methods in reinforcement learning through this comprehensive lecture. Delve into stochastic policies, supervised learning techniques, and the stochastic gradient policy theorem. Gain insights into the derivation process and understand the approach used in AlphaGo. Recap key concepts and conclude with a thorough understanding of policy gradient algorithms and their applications in artificial intelligence.
Overview
Syllabus
Introduction
Recap
Stochastic Policies
Supervised Learning
Stochastic Gradient Policy Theorem
Derivation
Alphago Approach
Conclusion
Taught by
Pascal Poupart
