% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@MASTERSTHESIS{Aach:892991,
author = {Aach, Marcel},
title = {{D}eep {L}earning for {P}rediction and {C}ontrol of
{C}ellular {A}utomata in {U}nreal {E}nvironments},
school = {University of Cologne},
type = {Masterarbeit},
reportid = {FZJ-2021-02488},
pages = {76 pages},
year = {2021},
note = {Masterarbeit, University of Cologne, 2021},
abstract = {In this thesis, we show the ability of a deep convolutional
neural network to understand the underlying transition rules
of two-dimensional cellular automata by pure observation. To
do so, we evaluate the network on a prediction task, where
it has to predict the next state of some cellular automata,
and a control task, where it has to intervene in the
evolution of a cellular automaton to achieve a state of
standstill. The cellular automata we use in this case are
based on the classical Game of Life by John Conway and
implemented in the Unreal Engine. With the usage of the
Unreal Engine for data generation, a technical pipeline for
processing output images with neural networks is
established.Cellular automata in general are chaotic
dynamical systems, making any sort of prediction or control
very challenging, but using convolutional neural networks to
exploit the locality of their interactions is a promising
approach to solve these problems. The network we present in
this thesis follows the Encoder-Decoder structure and
features residual skip connections that serve as shortcuts
in between the different layers. Recent advancements in the
field of image recognition and segmentation have shown that
both of these aspects are the key to success.The evaluation
of the prediction task is split into several levels of
generalization: we train the developed network on
trajectories of several hundred different cellular automata,
varying in their transition rules and neighborhood sizes.
Results on a test set show that the network is able to learn
the rules of even more complex cellular automata (with an
accuracy of ≈ $93\%).$ To some extent, it is even able to
interpolate and generalize to completely unseen rules (with
an accuracy of ≈ $77\%).$ A qualitative investigation
shows that static rules (not forcing many changes in between
time steps) are among the easiest to predict.For the control
task, we combine the encoder part of the developed neural
network with a reinforcement agent and train it to stop all
movements on the grid of the cellular automata as quickly as
possible. To do so, the agent can change the state of a
single cell per time step. A comparison between giving back
rewards to agents continuously and giving them only in the
case of success or failure shows that Proximal Policy
Optimization agents do better with receiving sparse rewards
while Deep Q-Network agents fare better with continuously
receiving them. Both algorithms beat random agents on
training data, but their generalization ability remains
limited.},
cin = {JSC},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {511 - Enabling Computational- $\&$ Data-Intensive Science
and Engineering (POF4-511)},
pid = {G:(DE-HGF)POF4-511},
typ = {PUB:(DE-HGF)19},
url = {https://juser.fz-juelich.de/record/892991},
}