Week five and the course rolls on to tackle planning and uncertainty Reinforcement learning, or how intelligent agents can deal with random environments, like public spaces and how they can be taught to overcome these challenges.
It’s illustrated quite nicely in this video below, one of the lectures from the course.
Unlike last week, which was a major struggle, the material benefited from more mini quizzes. At the risk of a very poor reinforcement learning pun, the quizzes do just that. They build on and test the content of the lectures. Without them some of the more complex mathematical problems tend to disappear over my head.
If Stanford listens to any feedback on this, it should be that the quizzes are really important and they can play a key role in providing greater understanding to the material being delivered.
Off to try and prepare for the mid-term…