Explore semi-Markov decision processes in this 36-minute lecture by Pascal Poupart. Delve into reinforcement learning concepts, queueing theory, and Bellman's equation. Learn about the option framework, transition dynamics, and reward functions as they relate to semi-Markov processes. Gain insights into the application of these concepts in decision-making scenarios and understand how they extend traditional Markov decision processes.
Overview
Syllabus
Introduction
Reinforcement Learning
SemiMarkov Processes
Queueing Theory
Bellmans Equation
Option Framework
Transition Dynamics
Reward Function
Options
Bellman Equation
Taught by
Pascal Poupart
