Exercise 5.3.3

Q-learning: find and fix errors in faulty pseudocode

Reinforcement Learning › Exercises › Lecture 5 · Model-Free Control › 5.3 Q-learning (off-policy learning)
EasyWritten

Algorithm 1 shows the pseudo-code of a faulty Q-learning algorithm. What are the problems in this Q-learning algorithm? Find at least four, explain what is wrong, and fix it.

algorithm pseudocode
Algorithm 1: Faulty Q-learning