kicked the animals out... not using anymore :-( DeepMind took it

Author: Pascal Brokmeier

src/chaps/body.tex

@@ -3,9 +3,6 @@ \chapter{Introduction}
 \input{chaps/methodology.tex}
 
 \chapter{Background}
-The thesis relies on work in three fields of research: Artificial Intelligence, Reinforcement Learning and (Animal)
-Cognition. The application of these fields happens in the field of competitive simulations, specifically an energy
-market simulation. 
 
 \input{chaps/artificialintelligence.tex}
 \subsection{Learning}
@@ -30,10 +27,6 @@ \section{Reinforcement Learning}
 \input{chaps/reinforcement.tex}
 
 %TODO still needed after paper by DeepMind? --> showed that learning from teacher helps
-%\section{Animal Cognition}
-%\subsection{Recognition}
-%\subsection{Memory}
-%\subsection{Social Cognition}
 
 %\section{Competitive Simulations}%as a tool of experimental research into AI
 

src/chaps/methodology.tex

@@ -1,14 +1,12 @@
 \section{Methodology}
-First, I will perform a literature research into the fields of \ac{AI}, \ac{RL} and Animal Cognition. In the field of AI
+First, I will perform a literature research into the fields of \ac{AI}, \ac{RL} and competitive simulations in energy
+markets. In the field of AI
 it's sub fields of \ac {SL}  and \ac {UL}  will be introduced. Here I will focus on the area of \ac{NN} and a form of
 \emph{learning}  called Backpropagation. In the field of \ac{RL} I will focus on the \ac{MDP} framework as well as the
 \ac{POMDP} subclass.  Next follows an introduction of the recent research in using \ac{NN} in \ac{RL} settings to allow
 for what is now called Deep Reinforcement Learning. This field has seen tremendous success in recent research, allowing
 for agents that successfully play Atari games and the game Go on superhuman levels of performance 
 \citep{proximalpolicyopt, silver2016mastering}.
-%TODO cite
-%TODO .
-%some explanation about the field of Animal Cognition and animal learning
 
 %After having introduced the basic research of \ac{AI} and \ac{RL}, I will summarize the state of research of Animal
 %Cognition, which focuses on how animals and humans learn, act and remember in their environment. Since humans and
@@ -17,7 +15,7 @@ \section{Methodology}
 %thesis, as many animals show forms of social learning, concepts of teaching and learning through observation.
 %TODO ref 
 
-Following the theoretical foundations,  I will introduce the concept of competitive simulations in research
+Following the theoretical foundations of \ac{AI},  I will introduce the concept of competitive simulations in research
 and summarize the \ac{PowerTAC} competition, it's parts and how agents (called brokers in the context of \ac{PowerTAC})
 make decisions. This includes an analysis of previous agents solution approaches.