deletions | additions       diff --git a/Introduction.tex b/Introduction.tex  index 6f0d7ae..8ad626b 100644  --- a/Introduction.tex  +++ b/Introduction.tex 
...
\section{Sheepherding}  Sheephearding is one of the oldest trades, where a herder (with help of one or multiple dogs) tries to herd sheep. bring sheep together at some target location.  In this project, we define a simplified model of sheepherding where dogs try to move sheep to a target.   We then use simulations and apply  reinforcement learning to train an AI for the dogs that is capable of performing several tasks related to sheepherding.If proven successful, we could replace herding dogs with drones that do all the sheepherding automatically.  \subsection{Literature}  \cite{Vaughan98robotsheepdog}\cite{ai_for_herding_sheep} First, we give a brief overview of some related literature.  In \cite{Vaughan98robotsheepdog}, a method is proposed to gather ducklings using a robot in a simple circular area, but their approach is not based on any learning.  \cite{ai_for_herding_sheep} does discuss methods for herging sheep from an AI perspective, where they use a hierarchical and stack-based finite state machine.  \cite{Schultz96robo-shepherd:learning} proposes to use genetic algorithms to fing decision rules to model robots behavior.   In a case study, one robot tries to guide another robot to a target location.  An interesting perspective is given in \cite{potter2001heterogeneity}, where so-called specialists are discussed.  Sometimes it is more useful for agents to specify in specific tasks (such as in playing soccer), while for other tasks this is not useful.  \cite{Utile:}