ML/AI - Reinforcement Learning & Q-Learning
Have you ever thought about understanding the basic concepts of Machine Learning & AI by doing some simple hands-on activities. In this course, we will focus on solving problem using Value Iteration.
Overview
Prerequisites
Issue with Value Iteration
Learning with experience
Discuss about Episode
Discuss about Queue (table)
Q-table
Challenge answer
Populate other values
Update cell logic
Challenge problem
Columns and Rows representation
Challenge answer
Recap
Agent learning process
Remembering experience
Test your understanding
Challenge answer
Test your understanding
Challenge answer
General Idea
Congratulations on completing this course!
Very informative as always!
Very informative as always!
Read LessBecause Q-learning is a form of MDP, maybe combining both modules might be beneficial
Because Q-learning is a form of MDP, maybe combining both modules might be beneficial
Read LessThe only part I'm slightly confused on is determining rewards because it sounds very arbitrary to me through the course explanations. Perhaps including some ...
Read MoreThe only part I'm slightly confused on is determining rewards because it sounds very arbitrary to me through the course explanations. Perhaps including some methods (in a reasonable manner if any exist) that modern AI programs or researchers use to determine the specific reward value would help. Otherwise, I liked and understood everything else!
Read LessI think the course overall was a nice 'break' after a rather challenging previous course. It was nice and laid back but the only thing would be that the cha...
Read MoreI think the course overall was a nice 'break' after a rather challenging previous course. It was nice and laid back but the only thing would be that the challenge problems are basically the same and maybe a little repetitive since it does ask the same thing a couple times
Read Less