Closed TheVeggydude closed 3 years ago
We define the goal of the agents to lower the infection amount to at least below some value infection_limit
. This could then set a limit for e.g. 10% of the population to be infected.
The reward function should reward achieving this state.
Our program does not have a clear goal state, because, as opposed to e.g. a maze, we don't have a clear end point.
We have do have some measure of success though, namely the number of infected people.