Overview
Explore the fundamentals of Reinforcement Learning in this comprehensive lecture by Emma Brunskill from Stanford University. Delve into the legacy of decision-making in AI and its impact on various fields such as robotics, society, and healthcare. Examine key concepts including Markov Decision Processes, decision policies, and reward functions. Gain insights into the challenges faced in AI planning, machine learning, and imitation learning. Understand the significant changes occurring in the field and their implications for future applications.
Syllabus
Introduction
Background
Legacy of Decision Making
Reinforcement Learning
Challenges in AI
Huge change in the field
Robotics
Society
Healthcare
Application Areas
AI Planning
Machine Learning
Imitation Learning
Challenges
Rough Plan
Markov Decision Processes
Decision Policies
Horizon
Reward Function
Taught by
Paul G. Allen School