Table of contents
Vacuum cleaner problem
Choose an action for the robot. Click on a box to make it dirty.
Simple cleaning robot
The robot will choose its own actions based on simple rules. Click on a box to make it dirty.
Rules for the agent to follow
The robot will follow the rules you choose. Click on a rule in the table to change it.
In this simple example there's only one set of rules that works well, but in more complex examples it won't be as obvious what set of rules to use. How would we find the rules?
We can choose a metric that evaluates how well the agent performs on the given problem.TODO: dirty/clean should be controlled automatically, reproducibly (seeded RNG), and then display a line chart with the performance measure