Delve into advanced concepts of reinforcement learning in this lecture from the Theory of Reinforcement Learning Boot Camp. Explore generative models, sample complexity analysis, value and Q equations, Q-learning, linear programming, and local planning techniques. Gain insights from experts Csaba Szepesvari and Mengdi Wang as they discuss topics such as lower bounds, JINI, Iron C4, and the Score Function Method. Enhance your understanding of planning and Markov Decision Processes in this comprehensive continuation of the series.
Planning and Markov Decision Processes - Part 2
Overview
Syllabus
Introduction
generative model
example
sample complexity
analysis
value equation
q equation
q function
q learning
Linear program
Lower bound
JIN
Iron C4
Local Planning
Score Function Method
Taught by
Simons Institute
Related Courses
-
Planning and Markov Decision Processes - Part 1
-
On the Statistical Complexity of Reinforcement Learning
-
Decision Making and Reinforcement Learning
-
Reinforcement Learning in Feature Space: Complexity and Regret
-
Provably Efficient Reinforcement Learning with Linear Function Approximation - Chi Jin
-
Online Learning in Markov Decision Processes - Part 2
