Re:Reinforcement Learning: An Introduction
by textlapse on Wednesday October 23, 2024 @04:15PM
(#41928904)
Basic probability/stats and some basic fundamentals around dynamic programming/recursion would be very helpful.
The big problem I found with this field is that the core ideas are very subtly built on top of each other. Without a proper teacher or an environment to study, self-study is much much harder.
With motivation as the primary reward in an environment where your actions are incremental progress will help you reach the goal of completing the core of this book.
(Past chapter 5, it should be a breeze as the foundation would have been strongly set)
The big problem I found with this field is that the core ideas are very subtly built on top of each other. Without a proper teacher or an environment to study, self-study is much much harder.
With motivation as the primary reward in an environment where your actions are incremental progress will help you reach the goal of completing the core of this book.
(Past chapter 5, it should be a breeze as the foundation would have been strongly set)