How to build your own reinforcement learning model with AnyLogic from scratch: Part 4 - the juicy details
In this fourth and last part, we go even deeper into model, exploring how the agents are created and how the algorithms make it all work. We focus on the actual Bellman equation and how it creates the actual learning effect.
Also, I now published the model source files below so you can download the core model and examine it yourself. Please note that all rights are reserved, so do not use this without my permission on anything but learning :-)
The video
The model
You can play with the model directly in your browser below:
The model source files
Now that you have hopefully also watched the previous videos, feel free to dive deeper into the model yourself. However, this is only for your personal learning, do not reproduce, share or reuse without my permission. And obviously, do not use it for real cars :D
Do let me know if this was helpful and if the video format is a better way to explain a model.