Last week, I started a four-part series exploring a simple reinforcement-learning model I build in AnyLogic. I decided to exclude any external libraries to help you learn how reinforcement-learning actually works.

What we cover in part 2

In this second part, I will introduce the model in more detail and we will dive deeper into the actual agents

Next week, we will check out actual code and then wrap up with the dynamic behavior of the model itself.

The video for part 2

You can view the first part below or directly on YouTube.

Play the model yourself

You can always run and play with the model yourself below or on the AnyLogic cloud here.

I would love to hear your feedback on this new format and what could be done differently. Would this be a good way to introduce more content in the future?

Have fun :-)