QLearning (month 5 · Weeks 1 and 2)

The goal of this two weeks is to solve the mountainCar problem using a reinforced learning algorithm with no neural network. Besides that, this blog will be refined to better show the work progress and learnings.

Lectures

• KL Divergence for Machine Learning

• Cross entropy loss explanation

• Unlearning phenomenom in machine learning

Lab work

• mountainCar openAIGym exercise with qlearning