\item \textbf{Shelves a posteriori:} The setup is similar to the previous one, but the PDDL problem file does not contain data about the shelves. Thus, these data will be learned by the intelligent agent via the move actions' reliability for the neighboring cells such as to be able to move around in the grid efficiently (while still having to avoid other agents).
\item \textbf{Maze:} The third setup is a randomly generated maze (see Fig.~\ref{fig:warehouse} on the right), where the intelligent agent does not know the layout of the maze but has to learn it through colliding with walls. Please note that since corridors are only one cell wide, it is not possible to bypass other agents. Thus there are no other agents in this setup.