Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the fundamentals of Partially Observable Reinforcement Learning in this 44-minute lecture by Pascal Poupart. Delve into key concepts including Markov Decision Processes, Observable RL, Model-Based RL, and Hidden Markov Models. Learn about the Optimization Problem, Belief Monitoring, and Separation in the context of Partial Observable ML. Gain insights into the challenges and techniques used in dealing with partially observable environments in reinforcement learning.
Syllabus
Intro
Markov Decision Processes
Partial Observable RL
Observable RL
ModelBased RL
Hidden Markov Model
Optimization Problem
Belief Monitoring
Separation
Partial Observable ML
Taught by
Pascal Poupart